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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    組織
    -0.07
    955
    -0.07
     Rarity
    -0.06
     слаб
    -0.06
     grup
    -0.06
     ου
    -0.06
     характер
    -0.06
     EQ
    -0.06
    组织
    -0.06
     चर
    -0.06
    POSITIVE LOGITS
    lıkları
    0.07
     woke
    0.06
    []):
    0.06
    DownList
    0.06
    /apis
    0.06
     údaje
    0.06
    ByName
    0.06
    気が
    0.06
    %',↵
    0.06
    %",↵
    0.06
    Act Density 0.056%

    No Known Activations