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

    Neuronpedia

    INDEX
    Explanations

    references to software packages

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

    package paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.48
    EDEFAULT
    -0.48
     bocca
    -0.46
    AlterField
    -0.45
     DBNull
    -0.45
    請繼續往下閱讀
    -0.43
     lion
    -0.40
    DBNull
    -0.40
    Diwedd
    -0.40
    vician
    -0.38
    POSITIVE LOGITS
    packages
    1.52
     packages
    1.20
     Packages
    1.09
    Packages
    1.05
     package
    0.96
     Package
    0.94
    パッケージ
    0.88
    package
    0.87
     PACKAGE
    0.86
    Package
    0.85
    Act Density 0.002%

    No Known Activations