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

    Neuronpedia

    INDEX
    Explanations

    stock splits, revision notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.73
    il
    0.62
    el
    0.61
    ol
    0.61
     and
    0.59
    est
    0.58
    k
    0.58
    '
    0.58
    oh
    0.57
    ans
    0.55
    POSITIVE LOGITS
    𝗚
    0.66
    𒁉
    0.60
     neoplasms
    0.59
    QK
    0.57
     mujhe
    0.56
     hesap
    0.55
     strListName
    0.54
    Beyblade
    0.53
    ಬ್
    0.52
     Idani
    0.52
    Act Density 0.000%

    No Known Activations