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

    Neuronpedia

    INDEX
    Explanations

    technical terms and variables related to programming and data processing

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

    code snippets closing parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.35
     Scalars
    -0.35
    esModule
    -0.34
     חיצוניים
    -0.32
    declare
    -0.30
    rap
    -0.30
    înes
    -0.29
    dotenv
    -0.29
     modes
    -0.29
     arşivlendi
    -0.29
    POSITIVE LOGITS
    DoubleQuotes
    0.59
    enderror
    0.56
    Бахар
    0.51
    bootstrapcdn
    0.51
     فريبيس
    0.50
     Numerade
    0.49
    éducation
    0.49
    NTIS
    0.49
    :✨
    0.48
     HasFactory
    0.48
    Act Density 0.238%

    No Known Activations