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

    Neuronpedia

    INDEX
    Explanations

    references to PDF documents and associated information

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

    File extensions (pdf, jpg)

    np_acts-logits-general · gemini-2.0-flash

    file extensions like pdf

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Xna
    -0.69
     ویکی‌پدی
    -0.63
    ContentAlignment
    -0.60
    SBATCH
    -0.60
     AssemblyVersion
    -0.59
    脚注の使い方
    -0.58
    ⓧ
    -0.56
     '\\;'
    -0.56
    zzleHttp
    -0.56
    UnitTesting
    -0.55
    POSITIVE LOGITS
     other
    0.60
    serviceWorker
    0.58
     Other
    0.54
    lha
    0.51
    mendation
    0.49
    (:,:,
    0.48
    bidities
    0.47
    other
    0.47
    ppets
    0.46
     שוליים
    0.46
    Act Density 0.145%

    No Known Activations