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

    Neuronpedia

    INDEX
    Explanations

    books and reading

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     piscinas
    -0.10
     moč
    -0.10
     airport
    -0.09
     aeroport
    -0.09
     inund
    -0.09
     koken
    -0.09
    anian
    -0.08
     timu
    -0.08
     clare
    -0.08
     dabar
    -0.08
    POSITIVE LOGITS
    一本
    0.18
     الكتب
    0.16
     paperback
    0.15
     বই
    0.15
     hardcover
    0.15
     一本
    0.15
     книги
    0.14
     Kindle
    0.14
     EPUB
    0.14
     പുസ്ത
    0.14
    Act Density 0.149%

    No Known Activations