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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that are used in personal emails or letters.

    oai_token-act-pair · gemini-2.0-flash

    we

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.74
    WriteTagHelper
    -0.65
    økt
    -0.64
    onViewCreated
    -0.63
    RegressionTest
    -0.62
    出版年
    -0.59
    Occurred
    -0.57
    Hentet
    -0.57
     disambiguazione
    -0.56
    قایناقلار
    -0.56
    POSITIVE LOGITS
     we
    1.97
     our
    1.66
     ourselves
    1.60
    We
    1.60
    我們
    1.57
    我们
    1.52
     We
    1.43
    we
    1.41
    我們的
    1.34
    私たち
    1.33
    Act Density 1.674%

    No Known Activations