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

    Neuronpedia

    INDEX
    Explanations

    counting heads and legs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    0.84
    ی
    0.83
    ه‌ی
    0.80
    ه
    0.80
    ش
    0.77
    一个
    0.75
    a
    0.75
     なっ
    0.74
    后来
    0.73
    з
    0.73
    POSITIVE LOGITS
     möchten
    0.84
    BURG
    0.81
     appla
    0.80
     ప
    0.79
    SHE
    0.77
     pudd
    0.77
    ING
    0.76
    ભગ
    0.74
    NOW
    0.73
     contiennent
    0.73
    Act Density 0.003%

    No Known Activations