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

    Neuronpedia

    INDEX
    Explanations

    represents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
     홀
    -0.08
    fills
    -0.08
    形成
    -0.08
     ओ
    -0.08
     sper
    -0.08
    Native
    -0.07
    �
    -0.07
    默
    -0.07
    -0.07
    POSITIVE LOGITS
    ansı
    0.08
     Williamson
    0.07
    0.07
     Nga
    0.07
     Dixon
    0.07
     Townsend
    0.07
     alguno
    0.07
    ರಿಗೆ
    0.07
     bell
    0.07
     Springer
    0.07
    Act Density 0.006%
    No Known Activations