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

    Neuronpedia

    INDEX
    Explanations

    dataframe glimpse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     QDom
    -0.08
    _RG
    -0.07
    SF
    -0.06
     Study
    -0.06
     aDecoder
    -0.06
     slož
    -0.06
    loser
    -0.06
    по
    -0.06
     Sof
    -0.06
     Fits
    -0.06
    POSITIVE LOGITS
    Ž
    0.07
    secs
    0.07
     incid
    0.06
     kök
    0.06
     whichever
    0.06
    aea
    0.06
     "..
    0.06
    based
    0.06
    RequiredMixin
    0.06
    γ
    0.06
    Act Density 0.002%

    No Known Activations