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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     genial
    0.46
     काय
    0.46
     rept
    0.46
     друг
    0.46
    Mét
    0.45
     headway
    0.44
     keen
    0.44
    ፣
    0.43
    Files
    0.42
    inya
    0.42
    POSITIVE LOGITS
    加えて
    0.52
    സ്ഥ
    0.48
    古
    0.48
    家
    0.47
     phù
    0.46
    书
    0.46
    更
    0.46
    الع
    0.44
    结束后
    0.44
    文章
    0.43
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.