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

    Neuronpedia

    INDEX
    Explanations

    Code calculations and rounding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    animation
    -0.07
     pulmonary
    -0.07
    anne
    -0.07
    ｵ
    -0.07
    أمان
    -0.07
    ANK
    -0.06
     women
    -0.06
     danced
    -0.06
     Space
    -0.06
     dall
    -0.06
    POSITIVE LOGITS
    郑
    0.08
    (Gravity
    0.07
     Pretty
    0.07
    首创
    0.07
    Rua
    0.07
    userService
    0.07
     Oriental
    0.06
    apolis
    0.06
     desp
    0.06
    欺负
    0.06
    Act Density 0.010%

    No Known Activations