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

    Neuronpedia

    INDEX
    Explanations

    mentions of points, especially bonus points, in what seems to be the context of reviews

    oai_token-act-pair · gemini-2.0-flash

    points

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.75
    WriteTagHelper
    -0.69
     umane
    -0.63
    getFirstName
    -0.61
     كومونز
    -0.59
    出版年
    -0.57
     equalTo
    -0.54
     Address
    -0.54
    vedať
    -0.54
     paraffin
    -0.53
    POSITIVE LOGITS
    <bos>
    0.82
     points
    0.73
     scored
    0.64
     bonus
    0.61
     scoring
    0.60
    queryInterface
    0.60
    Points
    0.60
    Scoring
    0.59
     الحره
    0.59
    ++)
    0.57
    Act Density 0.941%

    No Known Activations