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

    Neuronpedia

    INDEX
    Explanations

    Date

    np_max-act · gemini-2.0-flash

    The neuron fires on references to date‐and‐time code, especially tokens like year, month, day, date, and datetime calls.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    中心
    -0.06
    	fail
    -0.06
     Stunden
    -0.06
     Publisher
    -0.06
    евид
    -0.06
     Purs
    -0.06
    _Rect
    -0.06
     helm
    -0.05
    Subjects
    -0.05
     obtained
    -0.05
    POSITIVE LOGITS
    _LVL
    0.07
     amnesty
    0.07
     Nev
    0.07
     molding
    0.06
    @Json
    0.06
    /graph
    0.06
    ooter
    0.06
    dae
    0.06
    一样
    0.06
     breakpoints
    0.06
    Act Density 0.030%

    No Known Activations