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

    Neuronpedia

    INDEX
    Explanations

    percentage values and numeric representations in various contexts

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

    code and data symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     consultez
    -0.33
    太
    -0.29
    要
    -0.28
    aménagement
    -0.28
     jeunesse
    -0.28
     tutkim
    -0.28
     régimen
    -0.27
    "})
    -0.27
     retenir
    -0.27
    </u>
    -0.26
    POSITIVE LOGITS
    dafx
    0.73
    featureID
    0.72
    contentLoaded
    0.69
    ContentAlignment
    0.66
    0.65
    DoubleQuotes
    0.64
    EndGlobalSection
    0.63
    parsedMessage
    0.63
    انجليز
    0.62
     AssemblyTitle
    0.61
    Act Density 0.075%

    No Known Activations