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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blended
    -0.08
     arrows
    -0.07
     reckless
    -0.07
     spotted
    -0.06
    []{
    -0.06
    秩
    -0.06
     diffusion
    -0.06
    _ram
    -0.06
    خار
    -0.06
    ࿀
    -0.06
    POSITIVE LOGITS
    ldr
    0.07
    🇱
    0.07
    /sl
    0.07
    _aw
    0.07
    ﻷ
    0.07
     W
    0.07
    给人
    0.07
    ثير
    0.06
    وي
    0.06
     상
    0.06
    Act Density 0.007%

    No Known Activations