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

    Neuronpedia

    INDEX
    Explanations

    mathematical reasoning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     કરતાં
    -0.09
    来
    -0.08
    达
    -0.08
    最终
    -0.08
     કરતા
    -0.08
    lib
    -0.08
    这么
    -0.08
    从
    -0.08
    ichts
    -0.08
    优
    -0.07
    POSITIVE LOGITS
     Tal
    0.07
    azel
    0.07
    댓
    0.07
     Olivier
    0.07
     Albany
    0.07
     पॉ
    0.07
     Parr
    0.07
     установка
    0.07
    атели
    0.07
    ाइन
    0.07
    Act Density 0.077%

    No Known Activations