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

    Neuronpedia

    INDEX
    Explanations

    javascript selectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    1.11
    ل
    1.05
    k
    0.90
    c
    0.89
    л
    0.87
    of
    0.86
    ת
    0.83
    son
    0.82
    le
    0.80
    m
    0.80
    POSITIVE LOGITS
    ти
    0.75
     solcher
    0.74
     například
    0.72
    もら
    0.71
    も
    0.71
    列車
    0.70
     في
    0.70
     ktorí
    0.69
    யின்
    0.69
    ิ
    0.68
    Act Density 0.001%

    No Known Activations