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

    Neuronpedia

    INDEX
    Explanations

    fluctuations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lined
    -0.09
     totaled
    -0.08
     guud
    -0.07
     зах
    -0.07
     compt
    -0.07
    cstring
    -0.07
     coorden
    -0.07
     भेट
    -0.07
     yay
    -0.07
     crip
    -0.07
    POSITIVE LOGITS
     fluctuations
    0.16
     fluct
    0.12
     fluctuate
    0.12
     variability
    0.11
    变化
    0.11
     fluctu
    0.10
     unpredict
    0.10
     variations
    0.10
     swings
    0.09
    _vari
    0.09
    Act Density 0.023%

    No Known Activations