# Share a LIME Explanation — The Interactive One, Not a Screenshot

Canonical: https://commareports.com/share-lime-explanation
Published: 2026-09-14

> LIME writes a self-contained HTML explanation with the feature weights and the highlighted text. Publish it to Comma so the person questioning the model can actually read it.

# Share a LIME explanation

LIME exists for one conversation: someone does not believe a prediction, and
you have to show them why the model made it. That conversation almost never
happens with the person who ran the notebook — it happens with a product
manager, a risk reviewer, a domain expert, a regulator.

And the artifact that would settle it is sitting in a notebook cell.

```python
from lime.lime_tabular import LimeTabularExplainer

explainer = LimeTabularExplainer(X_train.values, feature_names=features,
                                 class_names=classes, mode="classification")
exp = explainer.explain_instance(X_test.iloc[42].values, model.predict_proba,
                                 num_features=10)
exp.save_to_file("explanation.html")
```

`save_to_file` writes a self-contained document — the weight chart, the class
probabilities, and for text models the document with the driving tokens
highlighted.

## Publish it

Drop `explanation.html` into [Comma](https://commareports.com/), or straight
from the notebook:

```python
import requests, os

requests.post(
    "https://commareports.com/api/v1/reports",
    headers={"Authorization": f"Bearer {os.environ['COMMA_API_TOKEN']}"},
    json={
        "title": "Why application 4471 was declined",
        "html": open("explanation.html").read(),
    },
).raise_for_status()
```

Scripts run inside a sandboxed iframe (`allow-scripts`, no `allow-same-origin`),
so the hover weights, the class toggle and the text highlighting all work at the
URL. See the [API reference](/docs/api).

## The interaction is the argument

A LIME explanation flattened to an image is a bar chart of feature names, and a
bar chart of feature names is exactly the thing people nod at without
understanding. What convinces is the interaction: switching the explained
class, reading the actual feature values next to their weights, seeing which
words in the document carried the classification.

That is the difference between "the model says decline" and "the model is
declining this because of a feature that is a proxy for something we are not
allowed to use" — which is a finding, and it only surfaces when the reviewer
can poke at the thing.

## Comments are the audit trail

Anchored threads put the domain expert's objection on the feature:

- "`days_since_last_contact` is a proxy for channel, not risk."
- "This instance is mislabelled in the training set — see ticket 812."

They stay attached across republishes, so when the model is retrained and the
explanation regenerated at the same URL, the history of what people objected to
is still there. For a model that has to be defended later, that trail is worth
more than the explanation itself. See [commenting on HTML](/comment-on-html).

## Treat it as sensitive

An explanation contains one instance's feature values. For anything
person-level that is personal data, so:

- Set access to **private or team**, never link-anyone.
- Publish the explanation for a redacted or synthetic instance when the point is
  the model's behaviour rather than this specific case.

See [sharing & access control](/docs/sharing).

## Limits

- **Entry HTML: 5 MB.** A text explanation over a long document can approach it;
  truncate the document or reduce `num_features`.
- Assets: 25 MB per file, **250 MB and 500 files total**.
- **60 requests/minute per token.**

## Try it

Comma is free — unlimited reports, unlimited commenters, unlimited revision
history.

**[Publish an explanation →](https://commareports.com/)**

### Related

- [Share a SHAP plot](/share-shap-plot) · [Share an Evidently report](/share-evidently-report)
- [Share a Deepchecks report](/share-deepchecks-report) · [Share a whylogs report](/share-whylogs-report)
- [Share an MLflow report](/share-mlflow-report) · [Share a Jupyter notebook as HTML](/share-jupyter-notebook-html)