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

    Neuronpedia

    INDEX
    Explanations

    page numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intoler
    -0.10
    anato
    -0.09
    .symmetric
    -0.09
    ตอบ
    -0.08
     Trudeau
    -0.08
    음
    -0.08
    .parsers
    -0.07
     extracurricular
    -0.07
    .SH
    -0.07
    utsu
    -0.07
    POSITIVE LOGITS
     页
    0.09
     الصفحة
    0.09
    頁
    0.09
     номер
    0.09
     페이지
    0.09
    _Page
    0.09
    Peb
    0.08
    .Page
    0.08
    ページ
    0.08
     litter
    0.08
    Act Density 0.012%

    No Known Activations