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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Review
    -0.74
    review
    -0.73
     whenever
    -0.72
     when
    -0.70
    when
    -0.66
     Review
    -0.66
     Silicon
    -0.65
    whenever
    -0.62
    REVIEW
    -0.61
     lorsqu
    -0.60
    POSITIVE LOGITS
    ers
    0.81
    Diweddarwch
    0.79
     виправивши
    0.77
     calendriers
    0.70
     للاسماء
    0.70
    CloseOperation
    0.68
     विश्वसनीयता
    0.66
    ImageContext
    0.66
    </tfoot>
    0.63
    TypedDataSet
    0.62
    Act Density 1.495%

    No Known Activations