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

    Neuronpedia

    INDEX
    Explanations

    Unstructured text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pect
    -0.07
    ного
    -0.07
     badly
    -0.06
     nuevo
    -0.06
     asserting
    -0.06
    arded
    -0.06
     inkl
    -0.06
    Gun
    -0.06
    ным
    -0.06
    JM
    -0.06
    POSITIVE LOGITS
     donating
    0.07
    [class
    0.07
    €€€€
    0.06
    /configuration
    0.06
     ราคา
    0.06
     آسیاب
    0.06
    (mid
    0.06
    """↵↵
    0.06
     resend
    0.06
     تصمیم
    0.06
    Act Density 0.000%

    No Known Activations