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

    Neuronpedia

    INDEX
    Explanations

    CC CB

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     size
    -0.07
     ix
    -0.07
    巡
    -0.07
    layout
    -0.07
    brook
    -0.06
    onestly
    -0.06
    Cast
    -0.06
     explore
    -0.06
    跳跃
    -0.06
    respect
    -0.06
    POSITIVE LOGITS
     APC
    0.07
    实体经济
    0.07
    LEGAL
    0.07
    �
    0.07
    RLF
    0.07
    瑁
    0.07
    言行
    0.07
    ARING
    0.06
    _linear
    0.06
    rün
    0.06
    Act Density 0.002%

    No Known Activations