Describe the bug
When asking for gradients for atoms beyond Rn the output is NaN.
I wonder if it is a bug.

To Reproduce
Steps to reproduce the behaviour:

1. happens with input (include input files): rah2ob.xyz has gradients as NaN

2. start dftd4 with (all the options here): dftd4 --func tpssh -c 2 --grad kk rah2ob.xyz

3. output showing the error: rah2ob.out

Please provide all input and output file such that we confirm your report.
ra_and_rn.zip
Expected behaviour
A clear and concise description of what you expected to happen.
I expected a result similar to the one in rnh2ob.out

Additional context
If I run dftd4 rah2ob.xyz there is no data for Ra in the "Atomic reference systems (in atomic units):" table.