Update app.py

app.py

@@ -194,7 +194,7 @@ iface = gr.Interface(
     ],
     outputs=gr.Image(label="Token Attribution Visualization"),
     title="AI Interpretability Explorer: See How Tokens Influence Predictions",
-    description="Input a prompt and target token to visualize token contributions using Integrated Gradients on LLaMA. "
+    description="Input a prompt and target token to visualize token contributions using [Integrated Gradients](https://captum.ai/docs/extension/integrated_gradients) on LLaMA. "
                                 "Explore model reasoning interactively.",
         # Insert a collapsible Feynman-style explanation and quick cheat-sheet actions using HTML so Gradio shows it above the app.
         # We use safe escaping for the cheat text when embedding into HTML/JS.
@@ -202,7 +202,7 @@ iface = gr.Interface(
         article="""
 ### How it works — Feynman-style
 
-This tool explains which input tokens most influence the model's next-token prediction using Integrated Gradients.
+This tool explains which input tokens most influence the model's next-token prediction using Integrated Gradients https://captum.ai/docs/extension/integrated_gradients.
 
 - What it does: Interpolates from a baseline to the actual input in embedding space, accumulates gradients along the path, and attributes importance to each input token.
 - Why it helps: Highlights which tokens push the model toward (green) or away from (red) the chosen target token. Useful for debugging, bias detection, and model transparency.