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

    Neuronpedia

    INDEX
    Explanations

    numbered lists or ratings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fift
    0.39
     புற்று
    0.36
     policym
    0.34
     다만
    0.34
     jack
    0.34
     እንዲሁ
    0.34
     みたい
    0.33
    BetMap
    0.33
     жөнүндө
    0.33
     。,
    0.33
    POSITIVE LOGITS
    =
    0.41
    k
    0.39
    -
    0.39
    is
    0.38
     are
    0.36
    注意
    0.35
     schedules
    0.35
    udir
    0.35
    是有
    0.35
     =
    0.34
    Act Density 0.053%

    No Known Activations