Semantic features are of different importance in concept representation. The concept elephant may be more easily identified from the feature <trunk> than from the feature <four legs>. We propose a new model of semantic memory to measure the relevance of semantic features for a concept and use this model to investigate the controversial issue of category specificity. Category-specific patients have an impairment in one domain of knowledge (e.g., living), whereas the other domain (e.g., nonliving) is relatively spared. We show that categories differ in the level of relevance and that, when concepts belonging to living and nonliving categories are equated to this parameter, the category-specific disorder disappears. Our findings suggest that category specificity, as well as other semantic-related effects, may be explained by a semantic memory model in which concepts are represented by semantic features with associated relevance values.