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

    Neuronpedia

    INDEX
    Explanations

    labels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    roupon
    -0.08
    ANGUAGE
    -0.07
     crude
    -0.07
    orent
    -0.07
    fluence
    -0.06
    اتی
    -0.06
    fname
    -0.06
     sensitivity
    -0.06
    ummy
    -0.06
     syncing
    -0.06
    POSITIVE LOGITS
    emotion
    0.07
    _DECLARE
    0.06
     GPLv
    0.06
     Components
    0.06
     Portug
    0.06
    ]+
    0.06
    创建
    0.06
    Illegal
    0.06
    -tm
    0.06
    >(↵
    0.06
    Act Density 0.137%

    No Known Activations