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

    Neuronpedia

    INDEX
    Explanations

    numerical or quantitative values and their significance in the text

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

    file diffs and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TemporalType
    -0.66
    parsedMessage
    -0.59
    Geplaatst
    -0.58
     yyq
    -0.57
    eqn
    -0.56
     صوتيه
    -0.56
     informée
    -0.56
    GraphicsUnit
    -0.54
    addCriterion
    -0.53
     arşivlendi
    -0.52
    POSITIVE LOGITS
     range
    0.34
     colombiana
    0.34
     colombiano
    0.33
    hezza
    0.32
    ToDecimal
    0.31
     discul
    0.31
    Equal
    0.30
    wsze
    0.30
     sélections
    0.30
    Kommentar
    0.30
    Act Density 0.006%

    No Known Activations