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

    Neuronpedia

    INDEX
    Explanations

    fragments or markers indicating code structure and documentation comments

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

    code comment delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.90
    parsedMessage
    -0.88
    featureID
    -0.82
    RegressionTest
    -0.79
     utafitiHapana
    -0.79
    delwed
    -0.78
    EDEFAULT
    -0.77
     autorytatywna
    -0.74
    addCriterion
    -0.73
     transfieras
    -0.71
    POSITIVE LOGITS
     Söhne
    0.33
    veröffentlichung
    0.31
     particularly
    0.29
    RenderAtEndOf
    0.27
     með
    0.27
    0.27
     käyttö
    0.27
    Ausgabe
    0.26
     often
    0.26
     including
    0.26
    Act Density 0.003%
    No Known Activations