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

    Neuronpedia

    INDEX
    Explanations

    Names related to Andrew/Anderson

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     KM
    -0.07
     xác
    -0.07
     Grave
    -0.07
     Fasc
    -0.07
    cmc
    -0.07
     Palace
    -0.07
    قی
    -0.07
     Tomb
    -0.07
     Quý
    -0.07
    cout
    -0.07
    POSITIVE LOGITS
     Anderson
    0.14
     Andrew
    0.13
     Andrews
    0.11
     Andre
    0.11
    Anderson
    0.11
    ander
    0.10
    and
    0.10
    Andrew
    0.10
     Andy
    0.09
     Andrea
    0.09
    Act Density 0.031%

    No Known Activations