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

    Neuronpedia

    INDEX
    Explanations

    books and reading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    businesses
    0.52
    pe
    0.44
    lysis
    0.43
     pobl
    0.43
    parency
    0.43
    યર
    0.43
    ZO
    0.43
    politics
    0.43
    िशनर
    0.43
     پاک
    0.42
    POSITIVE LOGITS
     Books
    1.46
     books
    1.41
     libros
    1.37
     книг
    1.34
     livros
    1.30
     BOOKS
    1.29
     кни
    1.28
    Books
    1.27
     книги
    1.26
     책
    1.25
    Act Density 0.203%

    No Known Activations