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

    Neuronpedia

    INDEX
    Explanations

    app interfaces and mockups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     വി�
    -0.09
     урож
    -0.09
     जोड़
    -0.09
     pigs
    -0.08
     образование
    -0.08
     छोड़
    -0.08
     усл
    -0.08
    ammad
    -0.07
     വിട്ട
    -0.07
     Unite
    -0.07
    POSITIVE LOGITS
     screenshot
    0.11
    截图
    0.09
    模拟
    0.09
     montr
    0.09
     screenshots
    0.09
     bezel
    0.09
     depicted
    0.09
     imagined
    0.08
    Screenshot
    0.08
     demos
    0.08
    Act Density 0.012%

    No Known Activations