==============================================================================
POWER SIMULATION -- naive_boxa_d0_5   [metric: # successes (count)]
==============================================================================
model: behavior ~ stim + day + stim:day + (1|rat)   (behavior = # successes (count); day within-window)
observed groups: stim n=3, control n=8   nrep=120, alpha=0.05
ground truth: stim:day=+6.403/day, rat SD=9.103, residual SD=12.48, days=6

 true stim:day interaction = +6.403 (100% of observed)
  N/group  | per-animal power | LME power
  ------------------------------------------
  3        |  0.36            |  0.77  <- observed
  5        |  0.79            |  0.92
  8        |  0.98            |  0.98  <- observed
  12       |  1.00            |  1.00
  16       |  1.00            |  1.00
  24       |  1.00            |  1.00

 true stim:day interaction = +3.202 (50% of observed)
  N/group  | per-animal power | LME power
  ------------------------------------------
  3        |  0.11            |  0.24  <- observed
  5        |  0.26            |  0.39
  8        |  0.44            |  0.51  <- observed
  12       |  0.69            |  0.74
  16       |  0.82            |  0.84
  24       |  0.95            |  0.94

Read the per-animal column as the honest power; LME is optimistic (obs-level DF).
