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

    Neuronpedia

    INDEX
    Explanations

    origin myths and cushioning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    0.86
     It
    0.71
     on
    0.67
    k
    0.64
    i
    0.61
    il
    0.60
    r
    0.59
    t
    0.59
     to
    0.59
     a
    0.58
    POSITIVE LOGITS
    も
    0.71
    도
    0.70
    는
    0.66
    ке
    0.65
    もん
    0.64
     及び
    0.63
    АР
    0.63
    ة
    0.63
    ນ
    0.62
    の話
    0.61
    Act Density 0.000%

    No Known Activations