Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Code and file paths

    np_max-act · gemini-2.0-flash

    directive headers and code elements in source code snippets.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on decorative ASCII‐art comment blocks (e.g. large multi‐line banner comments).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    áh
    -0.07
    -legged
    -0.06
    -sided
    -0.06
     Actress
    -0.06
    MI
    -0.06
    eşil
    -0.06
    _subtitle
    -0.06
    lat
    -0.06
    -half
    -0.06
     Bazı
    -0.06
    POSITIVE LOGITS
    诚
    0.07
     diss
    0.06
     steward
    0.06
    ĩnh
    0.06
    誠
    0.06
     truncated
    0.06
    θηκε
    0.06
     ngoài
    0.06
    сыл
    0.06
     orientations
    0.06
    Act Density 0.146%

    No Known Activations