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

    Neuronpedia

    INDEX
    Explanations

    product listing details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     قد
    0.47
    Produkt
    0.47
     অর্ডার
    0.43
     وقد
    0.42
     product
    0.41
    product
    0.40
    Product
    0.40
     produkt
    0.40
     plástico
    0.40
    produkt
    0.40
    POSITIVE LOGITS
     DISE
    0.41
    databind
    0.38
    TiO
    0.37
     теле
    0.37
     Mün
    0.37
     installments
    0.37
    bindings
    0.37
    tit
    0.36
     Computing
    0.36
     renewables
    0.36
    Act Density 0.009%

    No Known Activations