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

    Neuronpedia

    INDEX
    Explanations

    color

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fits
    -0.08
     lows
    -0.06
    ustral
    -0.06
    bruary
    -0.06
     Kernel
    -0.06
    PACK
    -0.06
    burse
    -0.06
    _timing
    -0.06
    AAA
    -0.06
    皇
    -0.06
    POSITIVE LOGITS
    ,[],
    0.07
     manually
    0.07
    σιεύ
    0.07
    ｿ
    0.07
    preserve
    0.06
    .Min
    0.06
     كر
    0.06
    -China
    0.06
    арамет
    0.06
    reactstrap
    0.06
    Act Density 0.001%

    No Known Activations