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

    Neuronpedia

    INDEX
    Explanations

    qualitative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Indexer
    -0.09
    Pixel
    -0.08
     Democratic
    -0.07
     RGB
    -0.07
     sen
    -0.07
     знать
    -0.07
     imperial
    -0.07
     Sen
    -0.07
     object
    -0.07
    navigate
    -0.07
    POSITIVE LOGITS
     ಮಹಿಳ
    0.09
    ತ್
    0.09
     ಸಂದ
    0.08
    ಿಸಿದ್ದ
    0.08
     ರೂಪ
    0.08
    ಾಕ್
    0.08
     kvinne
    0.08
    ಪ್
    0.08
    .toast
    0.08
     žene
    0.08
    Act Density 0.002%

    No Known Activations