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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to computational or scientific measurements and models

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

    followed by punctuation or parenthesis

    np_acts-logits-general · gemini-2.0-flash

    technical terms and specific domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AspNetCore
    -0.65
    webElementXpaths
    -0.62
     ModelExpression
    -0.55
    expandindo
    -0.54
     Италијани
    -0.53
    DrawerToggle
    -0.53
     Wikimedijinoj
    -0.53
     transfieras
    -0.52
    WebElementEntity
    -0.52
    GraphicsUnit
    -0.50
    POSITIVE LOGITS
    HandlerContext
    0.47
    esgue
    0.45
    atiker
    0.42
     teken
    0.39
    exitRule
    0.39
    rachtet
    0.38
    arXiv
    0.38
    basicConfig
    0.37
     zaken
    0.36
     XCTest
    0.35
    Act Density 4.432%

    No Known Activations