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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ftp
    -0.06
    اج
    -0.06
    Sugar
    -0.06
    교육
    -0.06
    mt
    -0.06
    ่ก
    -0.06
    –↵↵
    -0.06
     bize
    -0.06
     etc
    -0.06
     ∧
    -0.06
    POSITIVE LOGITS
     springfox
    0.07
     Singles
    0.07
     фундамент
    0.07
    ์เน
    0.06
    لع
    0.06
     bron
    0.06
     tohoto
    0.06
    .sorted
    0.06
     процессе
    0.06
     BRO
    0.06
    Act Density 0.188%

    No Known Activations