It is unclear if various types and domains of exercise have an identical effect on non-alcoholic fatty liver disease (NAFLD). Thus, this study aimed to investigate associations of different physical activity domains and muscle strength exercise with NAFLD using a nation-wide cohort database. Adults aged 20–79 years who participated in the Korean National Health and Nutrition Examination Survey between 2014 and 2018 were analyzed. Hepatic steatosis index was used to identify NAFLD. Physical activity was assessed with the Global Physical Activity Questionnaire. Of 21,015 participants, 4942 (23.5%) had NAFLD. Participants with ≥ 150 min/week of total physical activity had a lower risk of NAFLD than those with < 150 min/week (the fully adjusted OR: 0.86, 95% CI 0.78–0.95). When the individual domain of physical activity was assessed, ≥ 150 min/week of recreation activity was associated with a reduced risk of NAFLD (OR: 0.77, 95% CI 0.67–0.88), whereas ≥ 150 min/week of travel or work activity was not. The fully adjusted OR for NAFLD comparing participants with ≥ 2/week to those with < 2/week of muscle strength exercise was 0.83 (95% CI 0.73–0.94). Muscle strength exercise ≥ 2/week showed a lower risk of NAFLD for all levels of total and each specific domains of physical activity except for ≥ 150 min/week of work activity. An increased level of physical activity and muscle strength exercise was associated with a reduced risk of NAFLD, albeit the effect varied depending on domains of physical activity. Thus, physical activity should be differentiated by domains for the management of NAFLD. Muscle strength exercise could also be a good option for individuals who could not perform moderate-to-vigorous physical activity.