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

    Neuronpedia

    INDEX
    Explanations

    window

    np_max-act · gemini-2.0-flash

    The neuron detects references to the global `window` object (e.g. calls like `window.addEventListener` or `window.removeEventListener`).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     těl
    -0.06
     poměrně
    -0.06
    .puts
    -0.06
    特
    -0.06
    Utf
    -0.06
    ts
    -0.06
    德
    -0.06
     indicted
    -0.06
     Keith
    -0.06
     analsex
    -0.06
    POSITIVE LOGITS
     ${
    0.07
    =${
    0.07
    unched
    0.07
    ани
    0.06
     spreads
    0.06
    Wizard
    0.06
    负
    0.06
    LOUD
    0.06
     winning
    0.06
     json
    0.06
    Act Density 0.002%

    No Known Activations