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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PW
    -0.08
    jp
    -0.07
     QtWidgets
    -0.07
    AYOUT
    -0.07
    >V
    -0.07
    =context
    -0.07
    식
    -0.07
     JWT
    -0.07
    吃饭
    -0.07
     zwłas
    -0.07
    POSITIVE LOGITS
    不像
    0.08
     resembles
    0.07
    BOOLE
    0.07
    列为
    0.07
    首次
    0.07
    Layer
    0.06
    不算
    0.06
    驯
    0.06
    濉
    0.06
    bred
    0.06
    Act Density 0.008%

    No Known Activations