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

    Neuronpedia

    INDEX
    Explanations

    javascript

    np_max-act · gemini-2.0-flash

    elements related to technical documentation and programming queries.

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

    The neuron activates on the token “js,” i.e. occurrences of the JavaScript file-extension or script-file indicator.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    outh
    -0.07
    orth
    -0.07
    early
    -0.07
    iscard
    -0.07
     toutes
    -0.07
     skutečně
    -0.07
    mouth
    -0.07
     velké
    -0.07
     Patterson
    -0.07
    histoire
    -0.06
    POSITIVE LOGITS
     JS
    0.12
    js
    0.11
    -js
    0.09
    .js
    0.09
     js
    0.09
    JS
    0.09
    'S
    0.08
    (JS
    0.08
    /js
    0.08
    DS
    0.08
    Act Density 0.012%

    No Known Activations