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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Uso
    0.70
     For
    0.63
     Signific
    0.63
     इसलिए
    0.63
     ठ
    0.63
     الماضي
    0.62
     उत्साह
    0.62
     پ
    0.62
    woorden
    0.62
     Repl
    0.61
    POSITIVE LOGITS
    数据的
    0.86
     transversely
    0.83
    中小
    0.79
    एम
    0.79
    数据
    0.77
    ഐ
    0.77
    𝐎
    0.77
    考生
    0.75
    မျိုး
    0.74
    बी
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.