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

    Neuronpedia

    INDEX
    Explanations

    say "pages"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    摇
    -0.08
     deegaanka
    -0.08
     المرك
    -0.08
     bola
    -0.08
    .validators
    -0.08
    rats
    -0.08
     toxins
    -0.08
     livestock
    -0.08
    毒
    -0.08
     animaux
    -0.08
    POSITIVE LOGITS
     pages
    0.56
    _pages
    0.54
    Pages
    0.53
     páginas
    0.53
    pages
    0.51
     Pages
    0.51
    .pages
    0.50
     صفحات
    0.47
     страниц
    0.47
     paginas
    0.46
    Act Density 0.079%

    No Known Activations