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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     stets
    0.63
     величе
    0.61
     абсолютно
    0.60
     innumerable
    0.59
     обши
    0.57
     vigente
    0.57
     باقی
    0.56
     всегда
    0.54
     deepest
    0.54
     вновь
    0.54
    POSITIVE LOGITS
     يمكنك
    0.77
    你可以
    0.68
    สามารถ
    0.65
     يمكن
    0.63
    あなたの
    0.61
     도움이
    0.61
     your
    0.61
    あなたが
    0.61
    我可以
    0.60
     yardımcı
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.