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

    Neuronpedia

    INDEX
    Explanations

    Russian text/websites

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     따라
    -0.07
    oretical
    -0.06
    _bottom
    -0.06
     менше
    -0.06
     boyunca
    -0.06
     inflammation
    -0.06
     niños
    -0.06
     идет
    -0.06
     David
    -0.06
     bark
    -0.06
    POSITIVE LOGITS
    Writing
    0.06
    [--
    0.06
    ษ
    0.06
    (isinstance
    0.06
    ,“
    0.06
    ẩn
    0.06
    xca
    0.06
    ΟΠ
    0.06
    一级
    0.06
    _way
    0.06
    Act Density 0.009%

    No Known Activations