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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ла
    1.87
    of
    1.77
    ان
    1.76
    er
    1.71
    ي
    1.67
    ק
    1.63
    an
    1.60
    י
    1.53
    يي
    1.52
    ม
    1.52
    POSITIVE LOGITS
    ьте
    1.77
    的设计
    1.55
    getVisibility
    1.39
    的产品
    1.34
    Username
    1.32
    的同时
    1.31
    Message
    1.30
    ImageUrl
    1.29
    AN
    1.28
    BackgroundColor
    1.25
    Act Density 0.556%

    No Known Activations