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

    Neuronpedia

    INDEX
    Explanations

    books and publishing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    字符
    -0.07
     관한
    -0.07
    ？↵↵
    -0.07
    首
    -0.06
    Pal
    -0.06
    ождения
    -0.06
    дии
    -0.06
    城
    -0.06
     livre
    -0.06
    唯一
    -0.06
    POSITIVE LOGITS
    .MaximizeBox
    0.07
     Aş
    0.06
     tako
    0.06
     imb
    0.06
     numar
    0.06
     '('
    0.06
    exual
    0.06
    /is
    0.06
     HOWEVER
    0.06
    خدام
    0.06
    Act Density 0.045%

    No Known Activations