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

    Neuronpedia

    INDEX
    Explanations

    books, media, and language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Reporting
    0.78
    handleSubmit
    0.74
     Template
    0.71
    Reporting
    0.69
    Generator
    0.68
     template
    0.68
     placeholder
    0.66
     Generators
    0.65
     Assay
    0.65
    гистра
    0.64
    POSITIVE LOGITS
     books
    2.28
    books
    2.09
     libros
    2.06
     livros
    1.96
     book
    1.92
    Books
    1.92
     Books
    1.87
    书籍
    1.84
     libri
    1.82
     книг
    1.78
    Act Density 0.707%

    No Known Activations