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

    Neuronpedia

    INDEX
    Explanations

    to - as -

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     γεν
    1.04
     το
    1.01
     黒
    0.93
     로그인
    0.93
     α
    0.92
     Appet
    0.92
    ဗ
    0.90
     LOGIN
    0.90
     バ
    0.89
     △
    0.88
    POSITIVE LOGITS
    of
    0.78
    othed
    0.72
    based
    0.67
    where
    0.65
    Own
    0.64
    xiety
    0.63
    for
    0.62
    impossible
    0.62
     جاسک
    0.61
    Swim
    0.61
    Act Density 0.090%

    No Known Activations