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

    Neuronpedia

    INDEX
    Explanations

    punctuation and special characters in the text

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

    (VILI) causes macro

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.98
    出版年
    -0.94
    contentLoaded
    -0.88
    -0.82
     Administrativna
    -0.78
    InitVars
    -0.77
    IntoConstraints
    -0.77
    RegressionTest
    -0.77
     AssemblyCulture
    -0.77
    sizeCache
    -0.75
    POSITIVE LOGITS
     However
    0.34
     natomiast
    0.32
    1
    0.31
     Also
    0.30
    ).
    0.29
     But
    0.29
    )].
    0.29
    </em>
    0.29
    ↵↵
    0.29
     Palm
    0.28
    Act Density 0.141%

    No Known Activations