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

    Neuronpedia

    INDEX
    Explanations

    important names and entities within the text

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

    news and posts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     visibilité
    -0.37
     ciudadana
    -0.35
    <eos>
    -0.35
     extranjera
    -0.33
     ciudadanía
    -0.32
     Versorgung
    -0.30
     résistant
    -0.30
    holdet
    -0.29
    ENODEV
    -0.29
     adjunto
    -0.29
    POSITIVE LOGITS
     للمعارف
    0.66
    Hentet
    0.65
    الدراسه
    0.62
    Бахар
    0.59
    fjspx
    0.57
    Chham
    0.57
    المشاركات
    0.56
    الحياه
    0.56
    참고
    0.56
     चीज़ों
    0.56
    Act Density 0.053%

    No Known Activations