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

    Neuronpedia

    INDEX
    Explanations

    Oil and gas extraction

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of specific parts or spaces of a house or building (e.g., “downstairs area,” “crawlspace,” “insulation in home”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     مهند
    -0.08
    ProductId
    -0.07
     curso
    -0.06
    畫
    -0.06
    Calls
    -0.06
     depuis
    -0.06
     frankly
    -0.06
     Poh
    -0.06
    dbName
    -0.06
     органи
    -0.06
    POSITIVE LOGITS
     Jewelry
    0.06
    ул
    0.06
     acceptable
    0.06
    taient
    0.06
     сучас
    0.06
     aerospace
    0.06
     shape
    0.06
     bluetooth
    0.06
    сы
    0.06
    /*↵↵
    0.06
    Act Density 0.117%

    No Known Activations