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

    Neuronpedia

    INDEX
    Explanations

    games

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    荇
    -0.07
     feeling
    -0.07
    ัง
    -0.07
    胶
    -0.07
    诚实
    -0.06
     Real
    -0.06
    无力
    -0.06
    鲝
    -0.06
    .imshow
    -0.06
     bytes
    -0.06
    POSITIVE LOGITS
    DESC
    0.07
     П
    0.07
    ქ
    0.07
     scoped
    0.07
    クリ
    0.07
    /form
    0.07
    虾
    0.07
    -processing
    0.07
    dock
    0.06
    _SHOW
    0.06
    Act Density 0.188%

    No Known Activations