The source [Google post](https://www.blog.google/inside-google/company-announcements/...) says “ men were flagged for adjustments because they received less discretionary funds than women” so your 50/50 split of n is the most aggressive way to interpret that information.

More likely, we should interpret that to mean that men were found to be more likely to be underpaid (n_men > N_men), and that the appropriate comparison of variance (finding outliers) among men versus women was performed.