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

    Neuronpedia

    INDEX
    Explanations

    в

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    458
    -0.09
    839
    -0.08
    cp
    -0.08
    From
    -0.08
    _from
    -0.08
     LAP
    -0.07
    Regardless
    -0.07
    879
    -0.07
    adj
    -0.07
    nummer
    -0.07
    POSITIVE LOGITS
     ذكر
    0.09
     elaborado
    0.09
     Bear
    0.09
     наполн
    0.09
     References
    0.08
     частности
    0.08
     كون
    0.08
     Escorts
    0.08
     излож
    0.08
     авто
    0.08
    Act Density 0.002%

    No Known Activations