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

    Neuronpedia

    INDEX
    Explanations

    Numerical values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     исп
    -0.07
    癜
    -0.07
     PLAY
    -0.07
     ?",
    -0.07
     Ipsum
    -0.06
    _loss
    -0.06
     NoSuch
    -0.06
     imp
    -0.06
    Cumhur
    -0.06
    넘
    -0.06
    POSITIVE LOGITS
     blaze
    0.07
     Epidemi
    0.07
     earm
    0.07
    分区
    0.07
    جون
    0.07
     =================================================
    0.07
    .endpoint
    0.06
    .getProduct
    0.06
     위하여
    0.06
     Bai
    0.06
    Act Density 0.015%

    No Known Activations