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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cigarettes
    -0.09
    nonnull
    -0.09
    ellas
    -0.08
     Ebola
    -0.08
     edible
    -0.08
     melden
    -0.08
     electronic
    -0.08
     Straf
    -0.07
     volutpat
    -0.07
     elektronische
    -0.07
    POSITIVE LOGITS
    -mañ
    0.08
     बढी
    0.07
    :UITable
    0.07
     thu
    0.07
     بهترین
    0.07
     llawer
    0.07
     mů
    0.07
    :title
    0.07
     meira
    0.07
     朝
    0.07
    Act Density 0.003%

    No Known Activations