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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ри
    0.81
    ла
    0.79
    인
    0.76
    یتی
    0.75
    い
    0.74
    ל
    0.74
    .
    0.74
    لون
    0.72
    rict
    0.71
    ни
    0.71
    POSITIVE LOGITS
    ROP
    0.80
    gsub
    0.77
    MER
    0.69
     Deze
    0.69
    搬
    0.68
    生命
    0.68
     Trang
    0.68
    гаа
    0.67
    тные
    0.67
    ged
    0.66
    Act Density 0.000%

    No Known Activations