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

    Neuronpedia

    INDEX
    Explanations

    filenames

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    제도
    -0.07
     Classified
    -0.07
    מועמד
    -0.07
    .Str
    -0.06
    ﻭ
    -0.06
     boasts
    -0.06
    身上
    -0.06
    仍
    -0.06
    íg
    -0.06
    Outlet
    -0.06
    POSITIVE LOGITS
     revered
    0.08
    後來
    0.07
    سمي
    0.07
    鸧
    0.06
     Carrier
    0.06
    鳎
    0.06
    Svg
    0.06
    梳理
    0.06
     связи
    0.06
     Abrams
    0.06
    Act Density 0.063%

    No Known Activations