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

    Neuronpedia

    INDEX
    Explanations

    9

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    伭
    -0.08
    是中国
    -0.08
    (updated
    -0.07
     stati
    -0.07
     modulo
    -0.07
    .setStyle
    -0.07
     Latino
    -0.07
    首都
    -0.07
    一�
    -0.07
    ኮ
    -0.06
    POSITIVE LOGITS
    ------------
    0.09
    .sprites
    0.08
    WordPress
    0.08
    /pages
    0.07
    …
    0.07
     writer
    0.07
    ดร
    0.07
    売
    0.07
    抖
    0.07
    UILabel
    0.07
    Act Density 0.016%

    No Known Activations