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

    Neuronpedia

    INDEX
    Explanations

    street names

    np_max-act · gemini-2.0-flash

    references to community safety concerns and responses to violent incidents.

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

    The neuron activates on named geographic locations, especially proper‐noun street and place names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    otic
    -0.07
    Ｉ
    -0.07
     tùy
    -0.06
     데
    -0.06
     feasibility
    -0.06
     MPC
    -0.06
    ци
    -0.06
     multimedia
    -0.06
    анти
    -0.06
     tightening
    -0.06
    POSITIVE LOGITS
    :g
    0.07
     stem
    0.07
     fis
    0.07
    ادي
    0.06
     enlarge
    0.06
     disturb
    0.06
     blames
    0.06
     tensors
    0.06
     místní
    0.06
     veřejné
    0.06
    Act Density 0.015%

    No Known Activations