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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     southeast
    -0.07
     меня
    -0.07
     corrected
    -0.06
     switches
    -0.06
    accum
    -0.06
    cido
    -0.06
    Another
    -0.06
     races
    -0.06
     winding
    -0.06
    processed
    -0.06
    POSITIVE LOGITS
    Training
    0.07
     bieten
    0.06
     {!
    0.06
     عبار
    0.06
     "
    0.06
     BN
    0.06
    _ARROW
    0.06
     виник
    0.06
    рим
    0.06
     영어
    0.06
    Act Density 0.049%

    No Known Activations