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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     perse
    0.68
     прибы
    0.66
     invaluable
    0.61
    rawData
    0.60
     дорого
    0.58
     всеми
    0.57
     باوجود
    0.56
     архи
    0.56
     adaptación
    0.55
     principio
    0.55
    POSITIVE LOGITS
     I
    0.80
    I
    0.70
     写
    0.67
    lamiento
    0.66
     Acest
    0.65
    ESSMENT
    0.64
     这个
    0.64
    スナー
    0.63
    ließt
    0.63
    र
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.