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

    Neuronpedia

    INDEX
    Explanations

    deal

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the phrase “deal in” (as used in software license permission text).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    πτυ
    -0.07
    .custom
    -0.07
     Courier
    -0.06
    bots
    -0.06
     Sne
    -0.06
     BRO
    -0.06
    	atomic
    -0.06
     Fred
    -0.06
    entifier
    -0.06
    уры
    -0.06
    POSITIVE LOGITS
     Vik
    0.07
     Greece
    0.07
     NodeList
    0.06
    omes
    0.06
    pai
    0.06
    《
    0.06
     góp
    0.06
    .restaurant
    0.06
    (...)
    0.06
    ListModel
    0.06
    Act Density 0.001%

    No Known Activations