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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     saat
    -0.07
    зу
    -0.07
    anche
    -0.07
    /server
    -0.07
     lenguaje
    -0.07
    anch
    -0.07
    oug
    -0.07
     samedi
    -0.07
     निर्माता
    -0.07
     questa
    -0.07
    POSITIVE LOGITS
     반복
    0.13
     repeatedly
    0.10
    重复
    0.09
     recycled
    0.09
     ebb
    0.09
    不断
    0.09
     repetition
    0.08
     intermitt
    0.08
     తిర
    0.08
     reprises
    0.08
    Act Density 0.034%

    No Known Activations