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

    Neuronpedia

    INDEX
    Explanations

    legal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    綜合
    -0.08
    竞赛
    -0.07
    מז
    -0.07
    路口
    -0.07
    occ
    -0.07
    静脉
    -0.06
    酱
    -0.06
    usc
    -0.06
     Scripture
    -0.06
    降温
    -0.06
    POSITIVE LOGITS
    thrown
    0.07
     zobac
    0.07
     ведь
    0.07
    installed
    0.07
    .BLACK
    0.07
    珂
    0.07
    宁静
    0.06
    째
    0.06
    :inline
    0.06
    (FALSE
    0.06
    Act Density 0.013%

    No Known Activations