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

    Neuronpedia

    INDEX
    Explanations

    important pronouns and articles in the text

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

    numbers and specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Viitteet
    -0.44
    ViewFeatures
    -0.42
     Gerechtigkeit
    -0.37
    Espèce
    -0.36
     sekal
    -0.36
    棒
    -0.36
     Verpflichtung
    -0.35
     biografias
    -0.35
     cruzado
    -0.34
     Geschäftsführer
    -0.34
    POSITIVE LOGITS
     iNdEx
    0.52
    transQ
    0.50
    AndroidJUnit
    0.47
     transfieras
    0.47
    jspx
    0.45
     Arc
    0.44
    parsedMessage
    0.43
     ويكيميديا
    0.43
     jay
    0.41
    Bryce
    0.40
    Act Density 0.065%

    No Known Activations