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

    Neuronpedia

    INDEX
    Explanations

    references to specific ratings, reviews, or categories associated with questions or topics

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

    category names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.52
     فريبيس
    -0.50
    ViewFeatures
    -0.50
    expandindo
    -0.47
     cherchés
    -0.45
    makeConstraints
    -0.44
     AssemblyTitle
    -0.41
    GEBURTSDATUM
    -0.41
    ArgsConstructor
    -0.40
     HasFactory
    -0.40
    POSITIVE LOGITS
     enfans
    0.55
     engraçadas
    0.53
     Wikiseite
    0.47
    InputBorder
    0.45
    gameserver
    0.44
    complexContent
    0.43
     :)</
    0.42
    0.42
    󠁴
    0.42
     Garmin
    0.39
    Act Density 0.002%

    No Known Activations