Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code blocks or segments in a programming or technical document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ```json```

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ymce
    -0.68
     MainAxisSize
    -0.68
    UVWXYZ
    -0.66
    yarnpkg
    -0.65
    IContainer
    -0.65
    abank
    -0.64
    viders
    -0.63
     Duy
    -0.63
    wist
    -0.61
    bootstrapcdn
    -0.60
    POSITIVE LOGITS
    </code>
    0.66
    \]
    0.59
    </blockquote>
    0.54
    </table>
    0.45
    ↵↵↵
    0.43
    '}';
    0.41
    ↵↵↵↵↵
    0.41
     iconLine
    0.41
    };*/
    0.40
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.40
    Act Density 0.002%

    No Known Activations