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

    Neuronpedia

    INDEX
    Explanations

    internal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cous
    -0.08
    .class
    -0.07
    уль
    -0.07
     vill
    -0.07
     gentlemen
    -0.07
     dime
    -0.06
    Property
    -0.06
    华尔
    -0.06
    ierz
    -0.06
    馄
    -0.06
    POSITIVE LOGITS
     endured
    0.08
     UIKit
    0.07
    城
    0.07
    觞
    0.07
    	msg
    0.07
    ዞ
    0.07
     enorme
    0.07
     QMessageBox
    0.07
    豐
    0.07
    蒱
    0.06
    Act Density 0.011%

    No Known Activations