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

    Neuronpedia

    INDEX
    Explanations

    limiting processed foods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nutrition
    0.92
     nutritional
    0.87
     vitamins
    0.86
     Nutrition
    0.82
     macron
    0.81
     Nutritional
    0.80
     nutrient
    0.80
     nutrientes
    0.77
     hunger
    0.77
     Recovery
    0.74
    POSITIVE LOGITS
    Limit
    0.84
     limite
    0.81
    Limite
    0.78
     Limit
    0.76
    limit
    0.75
     límite
    0.75
     limitar
    0.74
     রঙিন
    0.73
     मर्यादा
    0.71
    সী
    0.70
    Act Density 0.112%

    No Known Activations