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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to internal processes and error handling in programming

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

    internal methods and extensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.82
    parsedMessage
    -0.75
    -0.69
    LabelTagHelper
    -0.65
     nahilalakip
    -0.65
    featureID
    -0.63
     surla
    -0.63
     للاسماء
    -0.60
    -------------</
    -0.60
    ViewImports
    -0.60
    POSITIVE LOGITS
    expandafter
    0.41
    SneakyThrows
    0.40
    ForResult
    0.40
    Ex
    0.39
     ge
    0.35
    fæ
    0.35
     مض
    0.33
    MethodImpl
    0.33
    geh
    0.32
     Mehr
    0.32
    Act Density 0.181%

    No Known Activations