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

    Neuronpedia

    INDEX
    Explanations

    Code/Technical snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     :)↵↵
    -0.07
     ktoś
    -0.07
    '.↵↵
    -0.07
    '}↵↵
    -0.07
    。。↵↵
    -0.07
     :)
    -0.07
    。↵↵
    -0.07
     ואין
    -0.06
     daß
    -0.06
     القرآن
    -0.06
    POSITIVE LOGITS
     disappe
    0.08
     restaur
    0.08
    建材
    0.08
    燥
    0.07
    пре
    0.07
     MediaPlayer
    0.07
     Supported
    0.07
     ATT
    0.07
    _CAPACITY
    0.07
    ToUpper
    0.07
    Act Density 0.632%

    No Known Activations