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

    Neuronpedia

    INDEX
    Explanations

    numerical values and percentages in the text

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

    Decimal numbers after periods

    np_acts-logits-general · gemini-2.0-flash

    numerical values and percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hauptartikel
    -0.71
    endregion
    -0.67
    Personensuche
    -0.67
    yntaxException
    -0.66
    بوابة
    -0.65
    .
    -0.65
     MainAxisSize
    -0.63
    tvguidetime
    -0.61
    LookAnd
    -0.61
     مشين
    -0.61
    POSITIVE LOGITS
    ">.
    0.70
    ()].
    0.64
     }}$.
    0.63
    *]
    0.61
     Melayu
    0.59
    >.
    0.59
    }.
    0.58
     */;
    0.58
    ）.
    0.57
    »).
    0.57
    Act Density 0.368%

    No Known Activations