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

    Neuronpedia

    INDEX
    Explanations

    specific tags and summaries in statistical and programming contexts

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

    test

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on programming- and technical-document tokens—file paths and filenames, code identifiers and keywords (includes, headers, request names), and other code/test section labels.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.48
    windowFixed
    -0.46
    webElementXpaths
    -0.46
    uxxxx
    -0.45
    GEBURTSDATUM
    -0.41
    @[+][
    -0.40
    yarnpkg
    -0.40
    SharedCtor
    -0.39
    Hentet
    -0.39
    AndroidJUnit
    -0.38
    POSITIVE LOGITS
    AxisSize
    0.47
    LEGGI
    0.47
    請繼續往下閱讀
    0.44
    TokenNameLBRACE
    0.44
    𝟸
    0.43
    Sklici
    0.43
    ̈́
    0.43
    ">//
    0.43
    aliers
    0.42
    garten
    0.42
    Act Density 0.214%

    No Known Activations