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

    Neuronpedia

    INDEX
    Explanations

    references to statistical or academic sources

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

    publications (e.g., year)

    np_acts-logits-general · gemini-2.0-flash

    citations and academic phrasing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.71
     '\\;'
    -0.61
    DoubleQuotes
    -0.56
    RegressionTest
    -0.56
    PropertyGroup
    -0.55
     TestBed
    -0.54
     step
    -0.53
    webElement
    -0.53
    chtenstein
    -0.52
    FXMLLoader
    -0.52
    POSITIVE LOGITS
     fubject
    0.75
     preſent
    0.71
     prefent
    0.64
     purpoſe
    0.63
     pleaf
    0.63
     occafion
    0.62
    CurrentUser
    0.60
     pleaſure
    0.59
     neceff
    0.59
     ſtate
    0.59
    Act Density 0.269%

    No Known Activations