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

    Neuronpedia

    INDEX
    Explanations

    code syntax / start tokens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    이며
    -0.07
     الصحفي
    -0.07
    ｀
    -0.07
    矸
    -0.07
    叙
    -0.07
    茆
    -0.07
     çeşitli
    -0.07
     jTextField
    -0.07
    ()',
    -0.07
    菲尔
    -0.07
    POSITIVE LOGITS
    (ro
    0.07
    .format
    0.07
     benefited
    0.07
     Sang
    0.07
    適合
    0.07
    سة
    0.07
    착
    0.07
    ﭷ
    0.07
    贿赂
    0.07
    享用
    0.06
    Act Density 0.013%

    No Known Activations