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

    Neuronpedia

    INDEX
    Explanations

    references to a product in various contexts

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

    product descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rodillas
    -0.41
     aislados
    -0.40
     accessibles
    -0.39
     Hälfte
    -0.39
     aislada
    -0.36
     Rücksicht
    -0.34
     Regelung
    -0.34
    GOTREF
    -0.34
    Cuánto
    -0.34
     halbe
    -0.33
    POSITIVE LOGITS
     Product
    1.18
     product
    1.17
    Product
    1.10
    PRODUCT
    1.02
    product
    1.00
     PRODUCT
    0.99
     Produkt
    0.98
     produkt
    0.90
    addProduct
    0.89
     produit
    0.88
    Act Density 0.009%

    No Known Activations