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

    Neuronpedia

    INDEX
    Explanations

    drink a glass of water

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     année
    2.11
     moons
    1.96
     ove
    1.93
     ys
    1.92
     prosecuted
    1.88
     ¹
    1.87
    饮料
    1.86
     zealand
    1.86
     предприятий
    1.86
     sockfd
    1.85
    POSITIVE LOGITS
    keiten
    1.97
    வோ
    1.65
    👉
    1.64
    HT
    1.60
    ्स
    1.59
    臾
    1.59
    دت
    1.59
    sel
    1.58
    چه
    1.57
    Gün
    1.55
    Act Density 0.006%

    No Known Activations