Inputs, weights, a sum, and an activation: one artificial neuron.
Rendering
\usetikzlibrary{arrows.meta, positioning}\begin{tikzpicture}[
node distance=6mm and 14mm,
every edge/.style={draw, -{Stealth}},
]
\node[circle, draw, minimum size=10mm] (sum) {$\Sigma$};
\node[left=of sum] (x2) {$x_2$};
\node[above=of x2] (x1) {$x_1$};
\node[below=of x2] (x3) {$x_3$};
\node[draw, right=of sum, minimum size=10mm] (act) {$\sigma$};
\node[right=10mm of act] (y) {$y$};
\path (x1) edge node[above] {$w_1$} (sum)
(x2) edge node[above] {$w_2$} (sum)
(x3) edge node[below] {$w_3$} (sum)
(sum) edge (act)
(act) edge (y);
\end{tikzpicture}