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

    Neuronpedia

    INDEX
    Explanations

    de

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    %m
    -0.07
    [i
    -0.07
     iface
    -0.07
    -area
    -0.06
    .N
    -0.06
     Fayette
    -0.06
    ीच
    -0.06
     curls
    -0.06
    ','-
    -0.06
    four
    -0.06
    POSITIVE LOGITS
    氏
    0.07
     de
    0.07
    Amb
    0.07
    ُل
    0.07
     CONTEXT
    0.07
     totalPages
    0.07
     눈을
    0.07
    ????
    0.06
     di
    0.06
     Amb
    0.06
    Act Density 0.018%

    No Known Activations