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

    Neuronpedia

    INDEX
    Explanations

    phone numbers

    np_max-act · gemini-2.0-flash

    The neuron activates on sequences of digits in contact details, effectively spotting phone numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _export
    -0.07
     meds
    -0.07
    Resizable
    -0.07
     Alerts
    -0.06
    Ч
    -0.06
    .window
    -0.06
    Cu
    -0.06
    ет
    -0.06
    News
    -0.06
    turtle
    -0.06
    POSITIVE LOGITS
     ιστο
    0.08
     сім
    0.07
    .connect
    0.07
    .runner
    0.06
     �
    0.06
    	DBG
    0.06
     지방
    0.06
    ลา
    0.06
     �
    0.06
    有一
    0.06
    Act Density 0.005%

    No Known Activations