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

    Neuronpedia

    INDEX
    Explanations

    sections of text that include mathematical or programming concepts

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

    LaTeX preamble

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    richTextPanel
    -0.66
     defaultstate
    -0.65
    Aholisi
    -0.60
    تقاوى
    -0.59
     виправивши
    -0.58
    GEBURTSDATUM
    -0.56
     незавершена
    -0.56
    IsMutable
    -0.56
    tagHelperRunner
    -0.54
    TestBed
    -0.53
    POSITIVE LOGITS
    ariConfig
    0.42
    FetchType
    0.41
    devamını
    0.37
    tissimi
    0.37
    rungsseite
    0.36
     Reisedaten
    0.36
     donker
    0.35
    weile
    0.35
    stdbool
    0.35
    .~(\
    0.35
    Act Density 0.034%

    No Known Activations