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

    Neuronpedia

    INDEX
    Explanations

    male reference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     remark
    -0.07
    (py
    -0.06
     followers
    -0.06
    About
    -0.06
     Luật
    -0.06
    ыва
    -0.06
     Assert
    -0.06
    -disc
    -0.06
     بتوان
    -0.06
    選手
    -0.06
    POSITIVE LOGITS
    isser
    0.07
    `),↵
    0.07
     compromises
    0.06
     pontos
    0.06
    ardım
    0.06
    概
    0.06
     Phú
    0.06
    找
    0.06
    통
    0.06
     mpl
    0.06
    Act Density 0.017%

    No Known Activations