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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron fires on standalone numeric tokens (e.g. integers or decimal numbers), effectively spotting number literals in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     merchants
    -0.07
    _size
    -0.07
     deepcopy
    -0.07
    8
    -0.07
    ases
    -0.07
     Availability
    -0.07
     status
    -0.06
     mock
    -0.06
     police
    -0.06
     jam
    -0.06
    POSITIVE LOGITS
    ेदन
    0.07
    .DropDown
    0.06
    รอง
    0.06
    omination
    0.06
     Bbw
    0.06
     aqu
    0.06
     HIS
    0.06
     Syn
    0.06
     문
    0.06
     synergy
    0.06
    Act Density 0.019%

    No Known Activations