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

    Neuronpedia

    INDEX
    Explanations

    race and ethnicity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    000
    -0.08
     serie
    -0.07
    最后
    -0.07
     Роз
    -0.07
     只
    -0.06
     cele
    -0.06
     believer
    -0.06
     KW
    -0.06
     '&'
    -0.06
    Cells
    -0.06
    POSITIVE LOGITS
    lean
    0.07
    ΑΓ
    0.07
    CppGeneric
    0.06
    ợ
    0.06
     لأ
    0.06
    RenderingContext
    0.06
    /core
    0.06
    ilmiştir
    0.06
    ücü
    0.06
    =a
    0.06
    Act Density 0.017%

    No Known Activations