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

    Neuronpedia

    INDEX
    Explanations

    note:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ่
    2.80
    не
    2.41
    ps
    2.16
    ae
    2.06
    ี
    2.03
    pais
    1.93
    az
    1.92
    ค์
    1.91
    ে
    1.90
    á
    1.87
    POSITIVE LOGITS
    tingham
    2.45
    将
    2.03
    ungsk
    2.00
    습니다
    1.95
    ۹
    1.93
    ول
    1.91
    彡
    1.90
    िफ्ट
    1.88
    ামুটি
    1.88
    ურთ
    1.84
    Act Density 0.385%

    No Known Activations