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

    Neuronpedia

    INDEX
    Explanations

    Manager

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of Android “*Manager” service classes (e.g. NotificationManager, AlarmManager)

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     purity
    -0.07
    _;
↵
    -0.06
    (sid
    -0.06
    .EOF
    -0.06
     Coroutine
    -0.06
     ز
    -0.06
     III
    -0.06
    -flow
    -0.06
     IV
    -0.06
     Receipt
    -0.06
    POSITIVE LOGITS
    affiliate
    0.07
     قتل
    0.06
    모
    0.06
    orderId
    0.06
    berra
    0.06
    _paragraph
    0.06
    -flag
    0.06
    aci
    0.06
    .namespace
    0.06
    .ValidationError
    0.06
    Act Density 0.004%

    No Known Activations