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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and quotation marks in text

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

    time durations, after numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bParam
    -0.45
     Inn
    -0.41
    ICHE
    -0.36
     Ess
    -0.35
     Cic
    -0.35
    referrer
    -0.35
    -0.34
    retry
    -0.34
    出版年
    -0.34
     ess
    -0.34
    POSITIVE LOGITS
    GEBURTSDATUM
    0.59
    ConstraintMaker
    0.56
    UnusedPrivate
    0.52
    RenderAtEndOf
    0.52
    Eksteraj
    0.52
    sizeCache
    0.51
    verwijspagina
    0.50
     محفوظة
    0.50
    KommentareTeilen
    0.49
    rungsseite
    0.48
    Act Density 0.013%

    No Known Activations