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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     infections
    -0.08
    zugehen
    -0.07
    .Migrations
    -0.07
     Jakob
    -0.07
     पक्ष
    -0.07
    棋
    -0.07
    оге
    -0.07
     polygon
    -0.07
    Ses
    -0.07
    Squ
    -0.07
    POSITIVE LOGITS
     სიტყვ
    0.10
     dheer
    0.09
     ნაწილი
    0.09
    holder
    0.09
     widths
    0.09
     airt
    0.09
     ს
    0.08
     nafasi
    0.08
    _len
    0.08
     მოკ
    0.08
    Act Density 0.004%

    No Known Activations