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

    Neuronpedia

    INDEX
    Explanations

    Scientific studies

    np_max-act · gemini-2.0-flash

    The neuron primarily responds to numeric expressions (e.g. section numbers, measurements, decimal values) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Yep
    -0.07
     pup
    -0.07
     selection
    -0.07
     Folding
    -0.06
    ifle
    -0.06
     별
    -0.06
    Reward
    -0.06
     mock
    -0.06
     Departments
    -0.06
     HAS
    -0.06
    POSITIVE LOGITS
     invokingState
    0.07
    earchBar
    0.06
    (parseInt
    0.06
     війсь
    0.06
    INSTALL
    0.06
     baktı
    0.06
     Stall
    0.06
    httpClient
    0.06
    smart
    0.06
    \GeneratedValue
    0.06
    Act Density 0.116%

    No Known Activations