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

    Neuronpedia

    INDEX
    Explanations

    Place names

    np_max-act · gemini-2.0-flash

    The neuron fires on proper nouns, especially place names (geographic locations).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    做
    -0.07
     DAN
    -0.07
     Digital
    -0.06
     Channel
    -0.06
     Property
    -0.06
     stimulates
    -0.06
    .Toggle
    -0.06
     negotiate
    -0.06
    (Api
    -0.06
    .params
    -0.06
    POSITIVE LOGITS
    Bag
    0.06
     prosec
    0.06
    аль
    0.06
    ACHE
    0.06
    ^\
    0.06
    .documentElement
    0.05
    ‌کننده
    0.05
     ers
    0.05
    寝
    0.05
     Russians
    0.05
    Act Density 0.129%

    No Known Activations