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

    Neuronpedia

    INDEX
    Explanations

    technical details related to software versioning and licensing information

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

    Lines of code/version control metadata

    np_acts-logits-general · gemini-2.0-flash

    version control metadata

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    -0.52
     as
    -0.50
    res
    -0.49
    ,
    -0.48
     or
    -0.48
    te
    -0.47
    ate
    -0.46
    ter
    -0.46
     while
    -0.45
    as
    -0.45
    POSITIVE LOGITS
     disambiguazione
    0.74
    httphttps
    0.73
     وتسجيلات
    0.73
     Италијани
    0.72
     autorytatywna
    0.68
     nahilalakip
    0.67
     חיצוניים
    0.66
     lenker
    0.66
    haikusbot
    0.65
    ----</
    0.65
    Act Density 0.318%

    No Known Activations