Lost in Activations: A Neuron-level Analysis of Encoders for Cross-Lingual Emotion Detection

AbstractThe rapid advancement of multilingual pre-trained transformers has fueled significant progress in natural language understanding across diverse languages. Yet, their inner workings remain opaque, especially with regard to how individual neurons encode and generalize semantic and affective features across languages. This paper presents an interpretability study of a fine-tuned XLM-R model for multilingual emotion classification. Using neuron-level activation analysis, we investigate the variance of neurons across labels, cross-lingual alignment of activations, and the existence of “polyglot” versus language-specific neurons. Our results reveal that while certain neurons consistently encode emotion-related concepts across languages, others show strong monolingual specialization.