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

    Neuronpedia

    INDEX
    Explanations

    +/-

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric measurements with decimal points (floating‐point numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Offline
    -0.07
    -functional
    -0.07
    Budget
    -0.07
     Manufacturers
    -0.06
    でしょう
    -0.06
     EQUAL
    -0.06
    Address
    -0.06
     lastName
    -0.06
     adverse
    -0.06
     Ethnic
    -0.06
    POSITIVE LOGITS
    _↵↵
    0.06
    ）↵↵
    0.06
    ="#"><
    0.06
     PMID
    0.06
    oppins
    0.06
    .exports
    0.06
     menacing
    0.06
    .git
    0.06
    !»
    0.06
     предмет
    0.06
    Act Density 0.020%

    No Known Activations