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

    Neuronpedia

    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is find four-digit year mentions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     cane
    -0.07
    ChangedEventArgs
    -0.07
     Microsoft
    -0.06
    igrants
    -0.06
     UserDefaults
    -0.06
    (conv
    -0.06
     Persons
    -0.06
    .tintColor
    -0.06
     plank
    -0.06
     NSLayoutConstraint
    -0.06
    POSITIVE LOGITS
    _DIST
    0.07
     yandan
    0.07
    /t
    0.07
    ..."
    0.07
    =R
    0.06
    尔
    0.06
     +(
    0.06
     超
    0.06
    boys
    0.06
    ферен
    0.06
    Act Density 0.037%

    No Known Activations