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

    Neuronpedia

    INDEX
    Explanations

    warranties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trek
    -0.07
     afford
    -0.07
    רגיש
    -0.07
     ROS
    -0.07
     Bust
    -0.07
    能耗
    -0.06
    出台
    -0.06
    insula
    -0.06
    ܫ
    -0.06
     blurred
    -0.06
    POSITIVE LOGITS
     pairwise
    0.07
    عامل
    0.07
     garlic
    0.07
     גיל
    0.07
    EW
    0.07
    自然而
    0.07
    _GR
    0.07
    师父
    0.07
    _SelectedIndexChanged
    0.06
     upp
    0.06
    Act Density 0.003%

    No Known Activations