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

    Neuronpedia

    INDEX
    Explanations

    lists and itemizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     soph
    -0.07
    Storyboard
    -0.07
    humidity
    -0.07
     Rena
    -0.07
     utterly
    -0.07
    Includes
    -0.06
     orbital
    -0.06
    vertise
    -0.06
    #pragma
    -0.06
     слу
    -0.06
    POSITIVE LOGITS
     ma
    0.07
    _FREQUENCY
    0.07
    视频
    0.06
     MUCH
    0.06
    "),
↵
    0.06
    ()))↵↵
    0.06
    豆
    0.06
    见
    0.06
    "}),↵
    0.06
    )).↵
    0.06
    Act Density 0.075%

    No Known Activations