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

    Neuronpedia

    INDEX
    Explanations

    metaphors and allegories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ўжо
    -0.09
     enfo
    -0.08
     rollers
    -0.08
     год
    -0.08
     Radios
    -0.08
     више
    -0.08
     зас
    -0.08
     touchdowns
    -0.08
     звон
    -0.08
     infar
    -0.08
    POSITIVE LOGITS
     metaphor
    0.09
     haga
    0.08
     qualquer
    0.08
     figur
    0.07
     puberty
    0.07
     fase
    0.07
     procrast
    0.07
     지나
    0.07
    figur
    0.07
     impurities
    0.07
    Act Density 0.056%

    No Known Activations