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

    Neuronpedia

    INDEX
    Explanations

    About people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prostitute
    -0.07
     iii
    -0.07
    ещ
    -0.06
     Yog
    -0.06
     stimulus
    -0.06
    費
    -0.06
     uncomfort
    -0.06
    .statusCode
    -0.06
    омер
    -0.06
     Voj
    -0.06
    POSITIVE LOGITS
    Handle
    0.07
    -dem
    0.07
     decltype
    0.07
    (tags
    0.06
    -east
    0.06
    unread
    0.06
     regarded
    0.06
    (draw
    0.06
     Gold
    0.06
    .partial
    0.06
    Act Density 0.125%

    No Known Activations