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

    Neuronpedia

    INDEX
    Explanations

    terms related to discounts and promotional offers

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

    coupon code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     juridiques
    -0.37
     fuertemente
    -0.32
     recueil
    -0.31
     explotación
    -0.31
     avancée
    -0.29
     suavemente
    -0.28
     detenidos
    -0.28
     conveniente
    -0.28
     fortemente
    -0.28
     Sprecher
    -0.28
    POSITIVE LOGITS
     مشين
    0.75
     birthday
    0.72
    tvguidetime
    0.71
     ModelExpression
    0.70
    RenderAtEndOf
    0.70
     Birthday
    0.69
    GeoNames
    0.68
     للاسماء
    0.67
    birthday
    0.67
    
    0.66
    Act Density 0.008%

    No Known Activations