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

    Neuronpedia

    INDEX
    Explanations

    messages

    np_max-act · gemini-2.0-flash

    This neuron detects terms related to incoming notifications or interruptions, such as new messages, alerts, calls, or unread items.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    検
    -0.08
     entertainment
    -0.07
    	password
    -0.07
    IRTH
    -0.06
    .purchase
    -0.06
    RF
    -0.06
    udd
    -0.06
    MB
    -0.06
    adlo
    -0.06
    rf
    -0.06
    POSITIVE LOGITS
    ,(
    0.07
     ور
    0.07
    şı
    0.06
     joystick
    0.06
    。当
    0.06
     cancer
    0.06
     تصميم
    0.06
    .basicConfig
    0.06
     creeping
    0.06
    ystick
    0.06
    Act Density 0.031%

    No Known Activations