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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    中国电信
    -0.09
    出了
    -0.08
     Iceland
    -0.08
     }),↵
    -0.07
    宝马
    -0.07
     aslında
    -0.07
     også
    -0.07
    American
    -0.07
    נז
    -0.07
    fav
    -0.07
    POSITIVE LOGITS
    ゑ
    0.07
    泌
    0.07
    澂
    0.07
    塄
    0.07
    ሊ
    0.07
    啸
    0.07
    켇
    0.06
    "&
    0.06
    usi
    0.06
    袅
    0.06
    Act Density 0.155%

    No Known Activations