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

    Neuronpedia

    INDEX
    Explanations

    references to file extensions and file manipulation functions

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

    languages and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.40
     
    -0.28
     [
    -0.28
     Sieben
    -0.27
    <h3>
    -0.26
     occasional
    -0.26
     respekt
    -0.25
    <strong>
    -0.24
     necesarias
    -0.24
    .
    -0.24
    POSITIVE LOGITS
    parsedMessage
    0.96
     ddelweddau
    0.92
    inSlope
    0.84
     kasarigan
    0.79
    writeFieldEnd
    0.76
    ésultats
    0.74
     propOrder
    0.74
    󠁴
    0.74
    tagext
    0.74
    Personendaten
    0.73
    Act Density 0.020%

    No Known Activations