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

    Neuronpedia

    INDEX
    Explanations

    deals

    np_max-act · gemini-2.0-flash

    The neuron fires on verbs that introduce what a patent (or technical provision) covers—e.g. “deals with,” “relates to,” “diz … respeito a,” etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Lik
    -0.07
    培
    -0.07
    iphertext
    -0.06
    亚
    -0.06
    (Source
    -0.06
    .Rec
    -0.06
     분석
    -0.06
    爆
    -0.06
    opened
    -0.06
    ptide
    -0.06
    POSITIVE LOGITS
     concern
    0.07
    dish
    0.07
     precinct
    0.07
     troublesome
    0.07
     concerns
    0.07
     xxx
    0.07
    veriş
    0.07
    .sale
    0.07
     PRICE
    0.07
     concerned
    0.06
    Act Density 0.041%

    No Known Activations