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

    Neuronpedia

    INDEX
    Explanations

    ethics, research guidelines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    均由
    -0.07
     COLOR
    -0.07
     Inspir
    -0.07
    panied
    -0.06
    岁以上
    -0.06
     Barcode
    -0.06
     prohibiting
    -0.06
     injust
    -0.06
    IfExists
    -0.06
    外套
    -0.06
    POSITIVE LOGITS
    מזרח
    0.07
    ,[],
    0.07
     ActionListener
    0.07
    Trip
    0.07
    موضوع
    0.07
    기술
    0.07
     Trey
    0.07
    횔
    0.07
    Those
    0.07
    _major
    0.06
    Act Density 0.002%

    No Known Activations