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

    Neuronpedia

    INDEX
    Explanations

    references to specific years and timeframes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    last year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TypedDataSet
    -0.66
    Diweddarwch
    -0.61
     onCreateView
    -0.61
    exitRule
    -0.57
    帖最后由
    -0.55
    AutoScale
    -0.55
    UAWEI
    -0.54
    findpost
    -0.54
    httphttps
    -0.53
    ReusableCell
    -0.53
    POSITIVE LOGITS
     måned
    0.47
     osallist
    0.43
    bleven
    0.40
     Meksika
    0.40
    ⓧ
    0.39
     lebaran
    0.39
     vastaan
    0.39
     vœux
    0.38
     tapaht
    0.38
    angkutan
    0.38
    Act Density 0.014%

    No Known Activations