fix `brainpy.math.softplus` and `brainpy.dnn.SoftPlus`

[chaoming0625]

580

[Dr-Chen-Xiaoyu]

It seems that threshold needs to be divided by beta “return jnp.where( x > threshold/beta , ...” , based on the description of softplus "input X beta > threshold"

[chaoming0625]

Exactly. Currently, the algorithm is:

jnp.where(x * beta > threshold, x, 1 / beta * jnp.logaddexp(beta * x, 0))

Thanks for the suggestion.