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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    स
    0.88
    د
    0.86
    ت
    0.84
    را
    0.81
    𒄿
    0.79
     önces
    0.79
    원
    0.77
    ्स
    0.77
    رب
    0.76
     aş
    0.76
    POSITIVE LOGITS
     больше
    0.81
     snowboard
    0.78
     сдела
    0.77
     Чтобы
    0.77
     экран
    0.76
     Также
    0.75
     Соответ
    0.75
     Але
    0.74
     Lizard
    0.74
     部
    0.73
    Act Density 0.000%

    No Known Activations