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

    Neuronpedia

    INDEX
    Explanations

    my

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    COR
    -0.07
     forbidden
    -0.06
    304
    -0.06
     develop
    -0.06
    Every
    -0.06
    EMPL
    -0.06
    310
    -0.06
     laws
    -0.05
     Lim
    -0.05
    優
    -0.05
    POSITIVE LOGITS
     framebuffer
    0.07
    ")]↵
    0.07
     Padding
    0.07
    uckland
    0.07
    lit
    0.07
    ViewSet
    0.07
    Swipe
    0.07
     ninete
    0.07
     tst
    0.07
     vzpom
    0.07
    Act Density 0.004%

    No Known Activations