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

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _edit
    -0.07
    ighted
    -0.07
     Zones
    -0.07
    桥
    -0.06
    %%%
    -0.06
    getattr
    -0.06
    ifornia
    -0.06
     США
    -0.06
     compan
    -0.06
     zones
    -0.06
    POSITIVE LOGITS
    (DIS
    0.07
     rushing
    0.07
     QMainWindow
    0.06
    奔
    0.06
     DE
    0.06
    /sm
    0.06
     draw
    0.06
    ducted
    0.06
     прот
    0.06
    /pro
    0.06
    Act Density 0.001%

    No Known Activations