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

    Neuronpedia

    INDEX
    Explanations

    Dates

    np_max-act · gemini-2.0-flash

    The neuron fires on date‐ and time‐format specifier tokens (things like “YYYY,” “MM,” “DD,” “HH,” “mm,” etc.) in localization/configuration strings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Employee
    -0.08
    �
    -0.07
     recommend
    -0.06
     Carrier
    -0.06
    Room
    -0.06
    灭
    -0.06
     değil
    -0.06
    sciously
    -0.06
     R
    -0.06
    ři
    -0.06
    POSITIVE LOGITS
     velik
    0.07
    이야
    0.07
     MouseEvent
    0.06
     drunken
    0.06
    -how
    0.06
    南
    0.06
    잡
    0.06
     हव
    0.06
    yyyy
    0.06
     cling
    0.06
    Act Density 0.004%

    No Known Activations