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

    Neuronpedia

    INDEX
    Explanations

    technical terms and phrases related to machine learning and algorithms

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

    technical terms and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    raise
    -0.47
     Wils
    -0.40
    agé
    -0.40
    Grab
    -0.40
     Previous
    -0.39
    சிய
    -0.39
     Grab
    -0.38
     missão
    -0.38
     Manuscripts
    -0.38
    Paradox
    -0.38
    POSITIVE LOGITS
    :✨
    0.66
     Wikimedijinoj
    0.63
    脚注の使い方
    0.56
    出版年
    0.54
    ViewInit
    0.50
    awtextra
    0.48
     AssemblyCulture
    0.48
    MigrationBuilder
    0.47
    verwijspagina
    0.46
    XtraBars
    0.45
    Act Density 0.091%

    No Known Activations