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

    Neuronpedia

    INDEX
    Explanations

    calories, carbohydrates, fat content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     workflows
    1.03
    Workflow
    1.00
     Workflow
    0.93
     Hardware
    0.90
    Hardware
    0.85
    硬件
    0.84
     успешно
    0.84
     iteratively
    0.84
    Successful
    0.84
     Appointments
    0.81
    POSITIVE LOGITS
     calories
    2.41
     calorie
    2.23
    calories
    2.02
     carbohydrate
    1.97
    calorie
    1.91
     carbohydrates
    1.89
     Calories
    1.89
     calorías
    1.80
    Calories
    1.80
     cholesterol
    1.75
    Act Density 0.236%

    No Known Activations