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

    Neuronpedia

    INDEX
    Explanations

    conditions related to algorithms, token validation, and contractual agreements

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

    specific numerical contexts

    np_acts-logits-general · gemini-2.5-flash-lite

    the neuron detects salient content words—important nouns and topic-bearing tokens in the text.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    Composable
    -0.40
    queryInterface
    -0.40
    KeySpec
    -0.40
    MenuInflater
    -0.40
    grafos
    -0.39
    vertisers
    -0.38
     يتيمه
    -0.37
     boobs
    -0.36
     فريبيس
    -0.36
    Personendaten
    -0.36
    POSITIVE LOGITS
    Välislingid
    0.63
    Sklici
    0.49
    parsedMessage
    0.47
    actéristique
    0.46
    NameInMap
    0.45
     ویکی‌پدی
    0.45
     isNameExpr
    0.43
    .*")]
    0.43
    dafx
    0.42
    ੝
    0.42
    Act Density 2.429%

    No Known Activations