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

    Neuronpedia

    INDEX
    Explanations

    references to safety and risk management in engineering contexts

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

    investigation of causes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dimensões
    -0.49
     normaux
    -0.44
     Constitutional
    -0.43
    เค้า
    -0.43
     nahilalakip
    -0.41
     felicità
    -0.41
     pleaſure
    -0.41
    Composição
    -0.41
     régulière
    -0.41
    IsMutable
    -0.40
    POSITIVE LOGITS
     betweenstory
    0.50
    enterOuterAlt
    0.49
    SPJ
    0.42
    endpush
    0.42
     causer
    0.41
     morti
    0.41
    Ŝ
    0.40
    +#+
    0.39
    CardHeader
    0.38
    最快更新
    0.38
    Act Density 0.025%

    No Known Activations