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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Else
    0.82
    Tokenizer
    0.77
    лизации
    0.77
    Tou
    0.77
     annan
    0.76
    pan
    0.75
    ILabel
    0.72
    ul
    0.71
     habilidades
    0.71
     enseñanzas
    0.71
    POSITIVE LOGITS
     regardless
    0.70
    锷
    0.68
     الأرض
    0.68
     сексуа
    0.68
     ١
    0.67
     Dems
    0.67
    そこ
    0.66
    ர்க்க
    0.65
     sqrt
    0.64
    イド
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.