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

    Neuronpedia

    INDEX
    Explanations

    punctuation or formatting characters

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

    often followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.49
     disambiguazione
    -0.45
     ویکی‌پدیای
    -0.45
     للمعارف
    -0.45
    новништво
    -0.44
     صوتيه
    -0.41
     disponibilités
    -0.40
    saraba
    -0.40
    Referanser
    -0.40
    rawDesc
    -0.39
    POSITIVE LOGITS
    migrationBuilder
    0.51
    ienė
    0.44
     betweenstory
    0.43
    parsedMessage
    0.43
    ReactDOM
    0.42
    utilisons
    0.42
     Imper
    0.42
    Imper
    0.41
    runApp
    0.41
     Dalai
    0.41
    Act Density 0.048%

    No Known Activations