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

    Neuronpedia

    INDEX
    Explanations

    terms related to customization and personalization

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

    artificial and automated systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ducción
    -0.56
     idéia
    -0.49
     duquel
    -0.49
     cubierto
    -0.47
     trilha
    -0.47
    ніципалі
    -0.46
     laquelle
    -0.46
     pinulongan
    -0.46
    Conclusiones
    -0.46
     Lesen
    -0.45
    POSITIVE LOGITS
     الحره
    0.49
    SBATCH
    0.47
     continúas
    0.47
    COUVER
    0.46
    Xna
    0.43
     desertcart
    0.42
    깐
    0.42
     للاسماء
    0.41
     contextLoads
    0.40
    abetes
    0.38
    Act Density 0.068%

    No Known Activations