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

    Neuronpedia

    INDEX
    Explanations

    default applications

    np_max-act · gemini-2.0-flash

    references to opening files and managing file-related tasks in programming contexts.

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

    The neuron activates on mentions of opening a file (or URL) with its default or associated application.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .keys
    -0.08
    shape
    -0.07
     accommodate
    -0.07
     mnohem
    -0.07
     출장
    -0.07
     лише
    -0.07
    ů
    -0.07
    ився
    -0.07
    füh
    -0.07
    �
    -0.06
    POSITIVE LOGITS
    unordered
    0.06
    _NUM
    0.06
     autobi
    0.06
    seau
    0.06
     projet
    0.06
    ooled
    0.06
    lingen
    0.06
    ruž
    0.06
    _batch
    0.06
     projekt
    0.05
    Act Density 0.010%

    No Known Activations