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

    Neuronpedia

    INDEX
    Explanations

    flag

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    杨
    -0.07
     meditation
    -0.07
     artisans
    -0.07
    녕하세요
    -0.06
     methane
    -0.06
     Chim
    -0.06
     Busty
    -0.06
    ="../
    -0.06
     Tooth
    -0.06
     Tues
    -0.06
    POSITIVE LOGITS
     Flag
    0.10
     flag
    0.10
     flags
    0.09
    flag
    0.08
    _flags
    0.08
    (FLAGS
    0.07
    Flag
    0.07
     Flags
    0.07
    (flags
    0.07
    FLAGS
    0.07
    Act Density 0.009%

    No Known Activations