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

    Neuronpedia

    INDEX
    Explanations

    After

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tournament
    -0.08
    pitch
    -0.07
    頻
    -0.07
     flipped
    -0.07
     fines
    -0.07
     frequency
    -0.07
     dosis
    -0.07
     Bren
    -0.07
    ->{'
    -0.07
     freq
    -0.07
    POSITIVE LOGITS
     Azərbaycan
    0.10
     বিমান
    0.08
     Azərbaycanın
    0.08
    _dependencies
    0.08
     dependencies
    0.08
     کرونا
    0.08
     کورونا
    0.08
     Augsburg
    0.08
     эв
    0.08
     السفر
    0.08
    Act Density 0.001%

    No Known Activations