A probe succeeds. What has been proven?

• The model uses the property when answering
• The property is readable at that layer
• The layer holds nothing else of interest

What does a probe train a small classifier to do?

• Read a property from a layer's activations
• Rewrite the model's weights
• Label brand-new training data

What does feature analysis ask about a direction?

• How fast it computes
• How many parameters it owns
• What human idea it stands for

Which intervention tests a claim about a circuit?

• Retrain the whole model from scratch
• Silence the part and check the behaviour breaks, then restore it
• Add extra layers around the part

Why does a single unit rarely match one human concept?

• Units usually fire for many unrelated inputs
• Units never activate while answering
• Concepts live only in the training data

A claim comes with no edit that could prove it wrong. How should you treat it?

• As a guess, not a finding
• As proven by its elegance
• As true until the model ships

A property a probe can read is always one the model uses.

Silencing a suspected circuit changes nothing, yet the team still credits it. What is wrong?

• The test needs a larger probe instead
• Correlation alone settles circuit claims
• The failing edit rejects the claim, so credit must go