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

    Neuronpedia

    INDEX
    Explanations

    Trust (zero trust architecture)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bia
    -0.08
    crest
    -0.08
     Ionic
    -0.08
    plotlib
    -0.08
     swell
    -0.07
     Tourism
    -0.07
    -0.07
     Milling
    -0.07
     soften
    -0.07
    beat
    -0.07
    POSITIVE LOGITS
    理念
    0.10
     հեռ
    0.09
    everyone
    0.08
    Everybody
    0.08
    .None
    0.08
     Everyone
    0.08
    ün
    0.08
     ներ
    0.08
    Everyone
    0.07
     ტელ
    0.07
    Act Density 0.001%
    No Known Activations