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

    Neuronpedia

    INDEX
    Explanations

    genetic mutations and variants

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Driver
    -0.06
     Чтобы
    -0.06
    enumerate
    -0.06
     Fury
    -0.06
    ใหญ
    -0.06
     всей
    -0.06
     toilets
    -0.06
    もしれない
    -0.06
    이어
    -0.06
     DATABASE
    -0.06
    POSITIVE LOGITS
    ẫn
    0.07
    uddenly
    0.07
    zek
    0.06
     kitchen
    0.06
    _plugins
    0.06
     修
    0.06
    escaping
    0.06
     consolidate
    0.06
     sám
    0.06
     희
    0.06
    Act Density 0.019%

    No Known Activations