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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     فرهنگی
    0.79
    doctoral
    0.77
    Chol
    0.74
     معاون
    0.73
     počas
    0.71
    ceral
    0.71
     heil
    0.71
    northern
    0.71
    Afrique
    0.71
     ngunit
    0.71
    POSITIVE LOGITS
    서
    0.97
    .
    0.97
    து
    0.88
    '
    0.88
    을
    0.84
    에
    0.82
    이
    0.80
    сть
    0.79
    рение
    0.78
    টি
    0.77
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.