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

    Neuronpedia

    INDEX
    Explanations

    book, textbook

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alanine
    0.80
    requencies
    0.78
     생성
    0.76
     нарушения
    0.76
    zeugung
    0.76
     emitters
    0.75
     amplitudes
    0.72
    pixel
    0.72
     impedance
    0.72
     Screenshot
    0.72
    POSITIVE LOGITS
     book
    3.33
     books
    3.22
     livro
    3.17
     libro
    3.17
     книга
    3.11
     книги
    3.04
    这本书
    2.99
     libros
    2.92
     کتاب
    2.92
     livros
    2.83
    Act Density 0.524%

    No Known Activations