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

    Neuronpedia

    INDEX
    Explanations

    references to technical processes or procedures

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

    scientific and technical terms

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

    structured, technical prose rich in formal sections, procedures, numeric details, and proper nouns—e.g., manuals, scientific/methods text, code definitions, and factual biographies with dates and places.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    HtmlAttribute
    -0.51
     старости
    -0.45
    MessageTagHelper
    -0.45
     '\\;'
    -0.43
    sfw
    -0.43
    setupUi
    -0.42
     MPR
    -0.40
    Aiheesta
    -0.40
     zuſammen
    -0.40
    TintMode
    -0.39
    POSITIVE LOGITS
    MigrationBuilder
    0.69
    hoeddwyd
    0.58
    Попис
    0.57
    OGND
    0.54
     للاسماء
    0.52
    IUrlHelper
    0.52
    Diweddarwch
    0.51
    Хьажоргаш
    0.49
    LookAnd
    0.49
    ViewFeatures
    0.49
    Act Density 22.511%

    No Known Activations