This paper proposes a technique to use on-chip event- or performance-counters to augment, or even replace, traditional analog CMOS temperature sensors. Using activity data from the performance counters, energy consumption that consequently causes heat dissipation can be tracked. Simple regression analysis permits us to find a relation between activity data and temperature. Performance counters already exist in many processors for debugging and performance characterization, require only minimal computation to interpret for temperature monitoring, and these calculations only need to operate at low frequency, so the marginal cost of this additional temperature-sensing capability is negligible. Performance counters monitor activity data (access count) of most on-chip functional units and therefore allow high-resolution, localized temperature sensing across a microprocessor. This in turn allows tracking of localized hotspots. Fine-grained, localized sensing is needed because different units can become hotspots depending on benchmarks. This is especially true if a malicious program intentionally induces high activity in a selected functional unit. This paper presents measurements from a commercial system to illustrate the accuracy of performance counters as additional temperature sensors.