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

    Neuronpedia

    INDEX
    Explanations

    .stringify

    np_max-act · gemini-2.0-flash

    JavaScript code that interacts with APIs using AJAX calls.

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

    The neuron mainly picks out numeric literals written as floating‐point decimals in code snippets.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    InOut
    -0.06
    _mac
    -0.06
    Lord
    -0.06
     "]"
    -0.06
    ió
    -0.06
     leaks
    -0.06
    (scene
    -0.06
    ests
    -0.06
    жен
    -0.06
     δύο
    -0.06
    POSITIVE LOGITS
    .stringify
    0.08
     kv
    0.07
     Batter
    0.06
    729
    0.06
    ))"↵
    0.06
     timeval
    0.06
    _sorted
    0.06
                  ↵
    0.06
    _species
    0.06
     NSMutable
    0.06
    Act Density 0.002%

    No Known Activations