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

    Neuronpedia

    INDEX
    Explanations

    powered by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    肖
    -0.07
     desirable
    -0.07
     sees
    -0.06
     inhib
    -0.06
     `[
    -0.06
     health
    -0.06
     perceived
    -0.06
     identity
    -0.06
    达到
    -0.06
    ダー
    -0.06
    POSITIVE LOGITS
     powered
    0.12
    -powered
    0.11
     Powered
    0.10
    Powered
    0.08
    powered
    0.08
     powering
    0.07
    (ti
    0.07
    bourg
    0.07
    Apache
    0.06
     Tup
    0.06
    Act Density 0.009%

    No Known Activations