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

    Neuronpedia

    INDEX
    Explanations

    tradition following, allowance without

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     s
    0.55
    s
    0.54
    E
    0.46
     audible
    0.46
     invited
    0.45
     yt
    0.44
     m
    0.43
     sn
    0.43
    A
    0.43
    %
    0.43
    POSITIVE LOGITS
    ವರೆಗೆ
    0.53
    ല്ലോ
    0.53
     إلى
    0.50
    gång
    0.50
    疥
    0.50
    нти
    0.49
    泓
    0.49
     ژان
    0.49
    鹵
    0.49
    țional
    0.47
    Act Density 0.001%

    No Known Activations