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

    Neuronpedia

    INDEX
    Explanations

    time travel

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the token “time” (particularly in contexts like “in time,” “travel in time,” “time of…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Ад
    -0.06
     天
    -0.06
    _ICON
    -0.06
     atol
    -0.06
    (tol
    -0.06
     WLAN
    -0.06
    ’ét
    -0.06
    眼睛
    -0.06
    -switch
    -0.06
     alleg
    -0.06
    POSITIVE LOGITS
     οι
    0.07
    .schedulers
    0.06
    traditional
    0.06
    ности
    0.06
     Connecting
    0.06
     основі
    0.06
     Activate
    0.06
    ост
    0.06
    (remove
    0.06
     अग
    0.06
    Act Density 0.011%

    No Known Activations