Output Layer (`outputLayerNode`)

Category: AI Model

Intended behavior

Final readout of the network: shows each incoming activation as a bar and outputs the index of the strongest neuron (the winner).

Inputs

ID	Label	Type	Unwired default
`in`	Activations	any	[]

Outputs

ID	Label	Type	Default
`out`	Values	any	undefined
`winner`	Winner	number	undefined

Configuration defaults

{}

Observed frontend behavior

This calls the production passive computation with the declared input/config defaults. Cached state, trigger execution and project wiring are separate.

{
  "kind": "passive-default-probe",
  "outputs": {
    "out": [],
    "winner": -1
  }
}

Observed backend behavior

Offline production passive computation with the same declared defaults; no device or model service is invoked.

{
  "kind": "passive-default-probe",
  "outputs": {
    "out": [],
    "winner": -1
  }
}

Current frontend implementation

Extracted production branches; helper calls and project execution context are defined in the referenced modules.

src/lib/execution-helpers.ts:332

case "outputLayerNode": {
      const xs = toNumberVector(inputs.in);
      outputs.out = xs;
      let winner = -1;
      for (let i = 0; i < xs.length; i++) {
        if (winner === -1 || xs[i] > xs[winner]) winner = i;
      }
      outputs.winner = winner;
      break;
    }

Implementation references

Verification limits

Default passive probe is an observation, not proof of all configurations, trigger behavior, or correctness. See ../NODE_RUNTIME_AUDIT.md and ../AUDIT_VALIDATION.md for test evidence.

Source fingerprint: 7e9d192bd3a559a7c50253919867601ef02c311d61e859f7afb4cadcfa508430. Rebuild with npm run docs:index.

FilesExpand file tree

outputLayerNode.md

Latest commit

History