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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to digital content and data performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Parts, coefficients, and edition names

    np_acts-logits-general · gemini-2.0-flash

    edition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ComVisible
    -0.77
    ftagPool
    -0.75
    Diweddarwch
    -0.73
     isComment
    -0.70
    scrapy
    -0.70
    Aiheesta
    -0.70
     يتيمه
    -0.69
    ViewFeatures
    -0.68
    aarrggbb
    -0.68
    PerformLayout
    -0.68
    POSITIVE LOGITS
     Edition
    0.65
    0.62
    zów
    0.54
     EDITION
    0.52
    ↵↵↵
    0.51
     edition
    0.50
     
    0.50
    了过去
    0.48
    .~(\
    0.47
    qrstuvwxyz
    0.46
    Act Density 0.849%

    No Known Activations