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

    Neuronpedia

    INDEX
    Explanations

    places where things are being arranged or done

    oai_token-act-pair · gemini-2.0-flash

    so

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     so
    -1.54
    <bos>
    -1.12
    so
    -1.03
    So
    -1.02
     So
    -1.02
     SO
    -0.85
     så
    -0.73
     כך
    -0.69
     soo
    -0.69
     così
    -0.69
    POSITIVE LOGITS
     فريبيس
    0.77
     Cæsar
    0.73
     myſelf
    0.66
    AlterField
    0.65
     bâtiments
    0.62
    ovács
    0.59
     Monfieur
    0.59
     EconPapers
    0.57
     Pernambuco
    0.57
     Mero
    0.57
    Act Density 5.225%

    No Known Activations