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

    Neuronpedia

    INDEX
    Explanations

    queries and conversations related to support or troubleshooting help

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

    questions and answers

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

    text that looks like Q&A/forum interface elements or metadata (e.g., "Best answer", "Ask a Question", usernames/tags, posting info).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.62
    principalTable
    -0.53
    AxisAlignment
    -0.49
     prioritise
    -0.46
     assurent
    -0.44
     AssemblyCulture
    -0.43
    shafen
    -0.43
    othed
    -0.42
     customizable
    -0.42
     parameterized
    -0.42
    POSITIVE LOGITS
    ThemeOverlay
    0.48
    DrawerToggle
    0.46
    VIAF
    0.45
    исленность
    0.39
    webElementXpaths
    0.39
    tagext
    0.38
     ویکی‌پدیای
    0.37
     okuyayım
    0.36
     ExecuteAsync
    0.35
    Notae
    0.35
    Act Density 0.405%

    No Known Activations