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

    Neuronpedia

    INDEX
    Explanations

    references to societal expectations and norms, particularly regarding women's roles

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

    Mentioning remaining silent/silence

    np_acts-logits-general · gemini-2.0-flash

    remain silent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.76
    värr
    -0.63
    tvguidetime
    -0.63
     ligiloj
    -0.61
    migrationBuilder
    -0.60
    Portail
    -0.59
    Зноскі
    -0.58
    DoubleQuotes
    -0.54
    Personensuche
    -0.54
    +#+#
    -0.54
    POSITIVE LOGITS
     silence
    3.01
     silent
    2.59
     Silence
    2.41
    silence
    2.35
    Silence
    2.28
     silencio
    2.15
     quiet
    2.15
    silent
    2.11
     Silent
    2.10
    Silent
    2.01
    Act Density 0.222%

    No Known Activations