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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and symbols typically used in formal proofs or theoretical discussions

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

    index tracking variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    省市镇
    -0.55
     FetchType
    -0.54
     tartalomajánló
    -0.53
    windowFixed
    -0.53
    expandindo
    -0.52
     Wikimedijinoj
    -0.52
    AddHtmlAttribute
    -0.51
    ➯
    -0.49
     cherchés
    -0.48
    Aholisi
    -0.48
    POSITIVE LOGITS
    Personendaten
    0.62
     mijne
    0.46
    GEBURTS
    0.45
    _,
    0.42
     _,
    0.40
    getragen
    0.39
     griech
    0.39
     âgées
    0.39
     quelcon
    0.38
    <?,
    0.38
    Act Density 0.306%

    No Known Activations