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

    Neuronpedia

    INDEX
    Explanations

    say "the ending -ary or -ified"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hôm
    -0.08
    rowning
    -0.07
    .SQLite
    -0.07
    ذهب
    -0.07
    瞄
    -0.07
     COMPLETE
    -0.06
    크
    -0.06
     tổng
    -0.06
    駐
    -0.06
     reinst
    -0.06
    POSITIVE LOGITS
    (theme
    0.07
     SERVICES
    0.07
     morality
    0.07
    典范
    0.07
    效能
    0.07
     Jackie
    0.07
    降温
    0.07
    應用
    0.07
     Panel
    0.07
    グループ
    0.07
    Act Density 0.002%

    No Known Activations