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

    Neuronpedia

    INDEX
    Explanations

    equity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mommy
    -0.08
     dedi
    -0.08
     sol
    -0.08
     સમાવેશ
    -0.08
     скор
    -0.08
     国内
    -0.08
     Domestic
    -0.08
     domestic
    -0.08
     ко
    -0.07
    Domestic
    -0.07
    POSITIVE LOGITS
     perceived
    0.09
     justiça
    0.08
     महसूस
    0.08
     cảm
    0.08
     perceptions
    0.08
    觉得
    0.08
     fairness
    0.08
     perception
    0.08
    clarations
    0.08
     injustice
    0.08
    Act Density 0.003%

    No Known Activations