The gradient is calculated by considering the Derivative of the Sigmoid function:

public double CalculateGradient(double? target = null)
{
  if (target == null)
    return Gradient = OutputSynapses.Sum(a =>a.OutputNeuron.Gradient * 
    a.Weight) * Sigmoid.Derivative(Value);

  return Gradient = CalculateError(target.Value) * Sigmoid.Derivative(Value);
}