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

    Neuronpedia

    INDEX
    Explanations

    food items and meals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     foods
    0.80
     foodstuffs
    0.75
     food
    0.73
    food
    0.73
     meats
    0.70
    食物
    0.69
     Foods
    0.66
     cheeses
    0.65
    foods
    0.65
    Foods
    0.65
    POSITIVE LOGITS
     विद
    0.46
     with
    0.46
    髋
    0.45
     demandé
    0.43
     NGO
    0.43
     עם
    0.43
     কন্যার
    0.42
    疗
    0.42
    stagram
    0.41
     Kenyatta
    0.41
    Act Density 0.039%

    No Known Activations