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

    Neuronpedia

    INDEX
    Explanations

    dictionaries

    np_max-act · gemini-2.0-flash

    The neuron fires on C++ snippets implementing a graph‐search/shortest‐path routine (e.g. use of priority_queue, vectors of neighbor pairs, distance arrays)—i.e. Dijkstra-style code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    장이
    -0.06
    .house
    -0.06
    ||(
    -0.06
     historically
    -0.06
    -0.06
    "This
    -0.06
    .mix
    -0.06
    您的
    -0.06
    Cal
    -0.06
     Wooden
    -0.06
    POSITIVE LOGITS
    ustralian
    0.07
     plano
    0.07
    Extent
    0.06
     Grove
    0.06
    (grammar
    0.06
    ясь
    0.06
    sterreich
    0.06
    (()=>{↵
    0.06
     OPTIONS
    0.06
     Revolutionary
    0.06
    Act Density 0.014%

    No Known Activations