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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    镰
    -0.08
    EMP
    -0.08
     начина
    -0.07
    teacher
    -0.07
     rope
    -0.07
     competitive
    -0.07
     proporcion
    -0.07
    技术支持
    -0.07
    出来的
    -0.07
     FRAME
    -0.07
    POSITIVE LOGITS
     nova
    0.07
    觑
    0.07
    paces
    0.07
    솊
    0.07
    过去
    0.07
     nearby
    0.07
    _common
    0.07
    [*
    0.07
     eclectic
    0.07
    路由
    0.07
    Act Density 0.064%

    No Known Activations