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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving products and their indices

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

    product, multiplication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     médié
    -0.52
    Meer
    -0.52
     ciudadana
    -0.51
     calefacción
    -0.49
     cálido
    -0.49
     telefónica
    -0.48
    Quieres
    -0.47
     aeropuerto
    -0.47
     democrática
    -0.47
     ciencia
    -0.47
    POSITIVE LOGITS
     prod
    2.13
    prod
    2.05
     Prod
    1.96
    Prod
    1.80
    PROD
    1.63
    ∏
    0.96
     PRODU
    0.95
     Produ
    0.93
     produt
    0.93
     produs
    0.93
    Act Density 0.012%

    No Known Activations