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

    Neuronpedia

    INDEX
    Explanations

    html class attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    畩
    0.72
    哐
    0.70
    pèce
    0.70
    níci
    0.68
    諰
    0.68
    ック
    0.67
     domést
    0.67
    谠
    0.67
     सीखना
    0.66
    箇所
    0.65
    POSITIVE LOGITS
    i
    1.04
    ي
    0.96
     been
    0.94
    ে
    0.87
     to
    0.84
    ="#"
    0.83
     had
    0.79
    н
    0.79
     is
    0.76
     on
    0.76
    Act Density 0.001%

    No Known Activations