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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ap
    -0.09
     apo
    -0.08
     hearth
    -0.08
    Acceler
    -0.07
     entrances
    -0.07
     Crimson
    -0.07
    stan
    -0.07
     ثابت
    -0.07
     katika
    -0.07
     extérieur
    -0.07
    POSITIVE LOGITS
     Allí
    0.12
     scegli
    0.09
     Hiermee
    0.09
     원하는
    0.08
     gewünsch
    0.08
     klicken
    0.08
    填写
    0.08
     disag
    0.08
     allí
    0.08
     регистрации
    0.08
    Act Density 0.032%

    No Known Activations