A three$-$class classification neural network computes a $4-$dimensional embedding $x$ at the penultimate layer, just before the final classification layer, as shown in the figure. This is followed by a weight matrix $W$ which computes an affine value $Z($also called a logit$)$ to which a softmax activation is applied to compute class probabilities. the weight matrix $W=\left[\begin{array}{ccc}1& 0& 1\\ 1& 1& 1\\ 0& 1& 1\\ 0& 1& 1\end{array}\right].$ What is the logit for class no$.2($assuming classes are numbered $12$ and $3$