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

    Neuronpedia

    INDEX
    Explanations

    high frequency numeric values in the text

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

    foreign words and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    səhifə
    -0.67
    Tembelea
    -0.66
     Autorisations
    -0.64
    onOptions
    -0.62
    endgroup
    -0.62
    ❵
    -0.61
    taminophen
    -0.60
    tachment
    -0.60
    parsedMessage
    -0.60
     Autorizaciones
    -0.59
    POSITIVE LOGITS
    0
    0.57
     armée
    0.46
     ennemi
    0.45
     pescoço
    0.43
     Veuillez
    0.43
     Norvège
    0.42
     frenos
    0.42
     grève
    0.42
    9
    0.41
     guerre
    0.40
    Act Density 0.075%

    No Known Activations