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

    Neuronpedia

    INDEX
    Explanations

    premises

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of specific physical network locations or equipment sites (e.g. customer premises, street cabinets, exchange points).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     uterus
    -0.07
    	stop
    -0.07
    orary
    -0.07
    fulness
    -0.07
    	base
    -0.06
    Lesson
    -0.06
     check
    -0.06
     matte
    -0.06
    woocommerce
    -0.06
    OutputStream
    -0.06
    POSITIVE LOGITS
    Evento
    0.07
    .sep
    0.06
    ichtet
    0.06
     lãi
    0.06
     pine
    0.06
    าญ
    0.06
     ‐
    0.06
     schem
    0.06
    ーブ
    0.06
    /course
    0.06
    Act Density 0.015%

    No Known Activations