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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的地
    -0.06
     goofy
    -0.06
    >();
    -0.06
     unparalleled
    -0.06
     GBP
    -0.06
     органів
    -0.06
     дит
    -0.06
    _cb
    -0.06
     가까
    -0.06
    に向
    -0.06
    POSITIVE LOGITS
    Lon
    0.07
    lated
    0.07
    covering
    0.06
     fonts
    0.06
     appended
    0.06
     chapter
    0.06
     учас
    0.06
     ACCEPT
    0.06
    čila
    0.06
     Va
    0.06
    Act Density 0.164%

    No Known Activations