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

    Neuronpedia

    INDEX
    Explanations

    text that indicates digital privacy or security information

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

    protected and subsequent descriptive phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.40
     సౌకర్య
    -0.38
    стоин
    -0.32
     @"/
    -0.32
     competição
    -0.29
     metav
    -0.29
    Akhir
    -0.28
     prefier
    -0.28
     ré
    -0.28
    Parcelize
    -0.28
    POSITIVE LOGITS
     isNameExpr
    0.91
    isNameExpr
    0.75
    期刊论文
    0.63
    NUMX
    0.62
    思議
    0.55
    }{*}{}
    0.55
    OGND
    0.54
     فريبيس
    0.52
     Wilayah
    0.50
     sanoo
    0.50
    Act Density 0.341%

    No Known Activations