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

    Neuronpedia

    INDEX
    Explanations

    video

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bý
    -0.07
    dispatcher
    -0.07
     byly
    -0.07
    рава
    -0.07
     jste
    -0.07
    rám
    -0.06
    رت
    -0.06
    lük
    -0.06
     Conc
    -0.06
    _marker
    -0.06
    POSITIVE LOGITS
     contributes
    0.07
     여기
    0.07
     ưu
    0.06
    없
    0.06
    <Category
    0.06
    479
    0.06
     sched
    0.06
    優
    0.06
    659
    0.06
    873
    0.06
    Act Density 0.002%

    No Known Activations