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

    Neuronpedia

    INDEX
    Explanations

    Punctuation in code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reputable
    -0.07
    Separ
    -0.06
    CUSTOM
    -0.06
    /Grid
    -0.06
    .exports
    -0.06
     CUSTOM
    -0.06
    ِي
    -0.06
    jid
    -0.06
    Pixels
    -0.06
    作品
    -0.06
    POSITIVE LOGITS
     );
    0.07
     signature
    0.07
    vehicle
    0.06
    ');↵
    0.06
     books
    0.06
     �
    0.06
     arts
    0.06
    _activation
    0.06
    //---------------------------------------------------------------------------↵↵
    0.06
    attering
    0.06
    Act Density 0.054%

    No Known Activations