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

    Neuronpedia

    INDEX
    Explanations

    occurrences of numbers and special characters

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

    dates and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enabling
    -0.40
     cejas
    -0.35
    FromNib
    -0.35
    djangoproject
    -0.34
    crisy
    -0.31
     conferir
    -0.30
     revealing
    -0.30
     Similarly
    -0.30
    theoremstyle
    -0.30
    有时
    -0.29
    POSITIVE LOGITS
    transQ
    0.68
    ReusableCell
    0.65
    KURZBESCHREIBUNG
    0.60
     EconPapers
    0.59
    sizeCache
    0.58
    ftagPool
    0.56
    contentLoaded
    0.56
    IContainer
    0.55
     AppCompatTheme
    0.55
    AddTagHelper
    0.54
    Act Density 0.001%

    No Known Activations