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

    Neuronpedia

    INDEX
    Explanations

    Category

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	RTLU
    -0.08
     seamlessly
    -0.07
    善于
    -0.07
    何时
    -0.07
    服务体系
    -0.07
     ),
    -0.07
    ဏ
    -0.07
     chào
    -0.07
     bene
    -0.07
    ).'</
    -0.07
    POSITIVE LOGITS
    started
    0.08
    Say
    0.08
    Northern
    0.08
    Err
    0.07
     matlab
    0.07
    icia
    0.07
    Specification
    0.07
    Making
    0.07
    箱子
    0.07
    _sets
    0.06
    Act Density 0.015%

    No Known Activations