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

    Neuronpedia

    INDEX
    Explanations

    technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Type
    -0.07
     tủ
    -0.06
    	len
    -0.06
    	ResultSet
    -0.06
     �
    -0.06
    oupper
    -0.06
     ince
    -0.06
    它们
    -0.06
     xen
    -0.06
      ↵    ↵
    -0.06
    POSITIVE LOGITS
     contribute
    0.08
    ERT
    0.07
     decent
    0.06
    askan
    0.06
    SPORT
    0.06
     Perception
    0.06
    ENCHMARK
    0.06
     державного
    0.06
     Disorders
    0.06
     밀
    0.06
    Act Density 0.000%

    No Known Activations