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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    носи
    -0.06
    島
    -0.06
    roups
    -0.06
    slug
    -0.06
    χω
    -0.06
    制作
    -0.06
    toBeTruthy
    -0.06
     lg
    -0.06
    。
↵
    -0.06
     newer
    -0.06
    POSITIVE LOGITS
    _LOADED
    0.07
     supers
    0.07
    ////////////////////////////////////////////////////////////
    0.06
     condol
    0.06
     supplying
    0.06
    =random
    0.06
    (bits
    0.06
     POINTER
    0.06
     funkc
    0.06
    下
    0.06
    Act Density 0.073%

    No Known Activations