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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     فشاں
    0.54
    ๓
    0.53
     Employee
    0.52
     Rated
    0.52
     نیٹ
    0.52
     மூல
    0.52
     Caribbean
    0.52
    鿌
    0.52
     نشان
    0.51
    സു
    0.51
    POSITIVE LOGITS
    '
    0.59
    <0xAC>
    0.55
    te
    0.54
     avait
    0.53
     artístico
    0.53
     dois
    0.52
     ascribe
    0.52
    ’
    0.52
     achat
    0.51
    要
    0.50
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.