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

    Neuronpedia

    INDEX
    Explanations

    references to promotional content and marketing materials

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

    promo and promotional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     grecque
    -0.55
     científicas
    -0.47
     entière
    -0.45
     Exteriores
    -0.45
    Enfin
    -0.44
     vrouw
    -0.44
     líquida
    -0.44
     completos
    -0.44
     Volkes
    -0.42
     kvinder
    -0.42
    POSITIVE LOGITS
     promo
    2.11
     Promo
    2.08
    Promo
    2.02
     promos
    1.73
    promo
    1.70
     promotional
    1.45
     Promotional
    1.40
     промо
    1.31
    Promotional
    1.29
     promotion
    1.23
    Act Density 0.002%

    No Known Activations