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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jason
    -0.06
    默认
    -0.06
    readOnly
    -0.06
    undles
    -0.06
     noble
    -0.06
    sizes
    -0.06
    (tokens
    -0.06
    кта
    -0.06
    -hero
    -0.06
    KG
    -0.06
    POSITIVE LOGITS
     tvor
    0.07
     owed
    0.07
    /original
    0.07
    Сам
    0.07
    %\
    0.07
     Brid
    0.06
     прес
    0.06
     далі
    0.06
    Yii
    0.06
     GUIDATA
    0.06
    Act Density 0.082%

    No Known Activations