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

    Neuronpedia

    INDEX
    Explanations

    population

    np_max-act · gemini-2.0-flash

    geographical and demographic information about administrative divisions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects section headings or subheadings (e.g., “Demographics”) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    شناس
    -0.07
     witnesses
    -0.07
    lines
    -0.07
    جوی
    -0.06
     empt
    -0.06
     lux
    -0.06
     Rub
    -0.06
    (chart
    -0.06
    itone
    -0.06
    _map
    -0.06
    POSITIVE LOGITS
     predecess
    0.06
    kých
    0.06
     obsc
    0.06
     anatomy
    0.06
     aws
    0.06
    ulnerable
    0.06
    _scaling
    0.06
     офі
    0.06
    -ли
    0.06
    ıda
    0.05
    Act Density 0.008%

    No Known Activations