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

    Neuronpedia

    INDEX
    Explanations

    does the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Š
    1.04
    ס
    1.01
    У
    1.00
    RE
    0.97
    ტი
    0.95
    ה
    0.93
    Đ
    0.93
    Ш
    0.92
    적인
    0.91
     外
    0.91
    POSITIVE LOGITS
     upbringing
    1.00
    credibly
    0.98
    नाडु
    0.93
    ﺩ
    0.93
    ль
    0.92
    us
    0.91
    sembled
    0.89
     nonstop
    0.87
    microwave
    0.86
     unforeseen
    0.84
    Act Density 10.874%

    No Known Activations