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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wrappers
    -0.07
     เกม
    -0.07
     scope
    -0.06
    AMESPACE
    -0.06
     cz
    -0.06
     gettext
    -0.06
     dro
    -0.06
     broaden
    -0.06
     boards
    -0.06
     ear
    -0.06
    POSITIVE LOGITS
    )])
    0.06
    ایت
    0.06
    FLAGS
    0.06
    arily
    0.06
    (predictions
    0.06
    だった
    0.06
    なた
    0.06
    ları
    0.06
     chỉnh
    0.06
    reserve
    0.06
    Act Density 0.001%

    No Known Activations