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

    Neuronpedia

    INDEX
    Explanations

    coffee and caffeine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     silica
    0.48
     freshwater
    0.48
     hydrogen
    0.47
     silic
    0.46
     температур
    0.46
     chilled
    0.46
     saline
    0.46
     ammonia
    0.45
     refill
    0.45
     water
    0.44
    POSITIVE LOGITS
     ട്ര
    0.46
     koff
    0.45
    Tob
    0.44
    uden
    0.44
    咖啡
    0.43
     Tob
    0.41
     Ethiopia
    0.40
     Ethiop
    0.39
    row
    0.38
     Ababa
    0.38
    Act Density 0.142%

    No Known Activations