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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     memes
    -0.07
    .*↵
    -0.07
     Sandy
    -0.07
     fantasies
    -0.07
     önem
    -0.06
     деятельности
    -0.06
    .tabs
    -0.06
     Tham
    -0.06
     ApplicationException
    -0.06
     reboot
    -0.06
    POSITIVE LOGITS
    (Color
    0.07
     permitted
    0.07
     Percentage
    0.06
    ندا
    0.06
     tries
    0.06
     electrom
    0.06
    NAS
    0.06
     Ads
    0.06
    性能
    0.06
    pch
    0.06
    Act Density 0.027%

    No Known Activations