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

    Neuronpedia

    INDEX
    Explanations

    Time units

    np_max-act · gemini-2.0-flash

    The neuron detects temporal references—words that denote dates or time (e.g. days of the week, months, “week,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     customerId
    -0.07
     页面
    -0.07
    /apimachinery
    -0.06
    282
    -0.06
     Иванов
    -0.06
     torment
    -0.06
    unchecked
    -0.06
    TestingModule
    -0.06
    People
    -0.06
     Од
    -0.06
    POSITIVE LOGITS
    ego
    0.07
    >The
    0.07
    LV
    0.07
    orca
    0.07
    ुओ
    0.06
     Called
    0.06
     pharmaceutical
    0.06
    루
    0.06
    альное
    0.06
     konnte
    0.06
    Act Density 0.048%

    No Known Activations