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

    Neuronpedia

    INDEX
    Explanations

    technical or structured data formats, particularly in programming or software contexts

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

    Code-related syntax and programming terms

    np_acts-logits-general · gemini-2.0-flash

    assembly, preprocessor, probability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fır
    -0.54
    zość
    -0.45
    elcome
    -0.44
    衛門
    -0.44
     pell
    -0.43
     виправивши
    -0.43
    CONSIN
    -0.43
     betweenstory
    -0.41
     papà
    -0.41
     society
    -0.41
    POSITIVE LOGITS
    IsContent
    0.84
    InjectAttribute
    0.83
     nahilalakip
    0.77
     numberWith
    0.75
    expandindo
    0.72
     Paglinawan
    0.72
    Билгалдахарш
    0.72
    település
    0.71
     Akismet
    0.70
     ModelExpression
    0.70
    Act Density 0.121%

    No Known Activations