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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    excel
    -0.06
    _'+
    -0.06
     Sends
    -0.06
     اقتص
    -0.06
     regained
    -0.06
     beers
    -0.06
    услов
    -0.06
    Come
    -0.06
    numbers
    -0.06
    ANTA
    -0.06
    POSITIVE LOGITS
    fred
    0.07
     använd
    0.07
     structured
    0.06
     adverse
    0.06
    ailing
    0.06
    iltro
    0.06
     کوت
    0.06
    -An
    0.06
    542
    0.06
     DecimalFormat
    0.06
    Act Density 0.000%

    No Known Activations