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

    Neuronpedia

    INDEX
    Explanations

    cataracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    實
    -0.08
    行動
    -0.08
     Relax
    -0.07
    橡胶
    -0.07
    不得已
    -0.07
    Functions
    -0.07
     urge
    -0.07
    螺
    -0.07
     manage
    -0.07
    緊
    -0.07
    POSITIVE LOGITS
    鄹
    0.08
    ]("
    0.08
     משחק
    0.07
     unaffected
    0.07
     skillet
    0.07
    ائ
    0.07
     constexpr
    0.07
    >:
    0.07
    越来越高
    0.07
     ?>/
    0.07
    Act Density 0.001%

    No Known Activations