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

    Neuronpedia

    INDEX
    Explanations

    medieval and historical periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trillions
    0.58
     trillion
    0.58
     billions
    0.57
     Nasdaq
    0.57
    TypeScript
    0.57
     Kayla
    0.56
     attualmente
    0.56
     TypeScript
    0.55
     కోట్ల
    0.55
     대한민국
    0.55
    POSITIVE LOGITS
    當時
    1.01
     medieval
    0.98
     aristocratic
    0.94
     Medieval
    0.93
     peasant
    0.91
    当时的
    0.90
     damals
    0.89
    Medieval
    0.89
    当时
    0.87
     peasants
    0.87
    Act Density 0.101%

    No Known Activations