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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    сці
    0.48
    лару
    0.45
    компа
    0.45
     एक्सरसा
    0.42
    飞机
    0.42
    每一
    0.42
    阿
    0.41
     satisfies
    0.41
    之时
    0.40
     Тыва
    0.39
    POSITIVE LOGITS
    uk
    0.46
     براہ
    0.43
    ürm
    0.43
    uzten
    0.43
    uke
    0.41
    ēng
    0.40
    olo
    0.40
     ชื่อ
    0.40
    ym
    0.39
    tex
    0.39
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.