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

    Neuronpedia

    INDEX
    Explanations

    Events at various locations

    np_max-act · gemini-2.0-flash

    This neuron fires on the main nominal labels describing the type of incident or its key actors/things in a news‐report context (e.g. “costume,” “carnival ride,” “law student,” “rafting guide,” “church carnival,” “factory wall,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     lamp
    -0.07
    、新
    -0.06
    (ai
    -0.06
    λμ
    -0.06
     constitutional
    -0.06
     เต
    -0.06
     Necklace
    -0.06
    unsubscribe
    -0.06
     соглас
    -0.06
     Quality
    -0.06
    POSITIVE LOGITS
     минут
    0.07
     AppComponent
    0.06
    .setView
    0.06
     "'.$
    0.06
    -ps
    0.06
    pped
    0.06
    	on
    0.06
     '$
    0.06
    maze
    0.06
    lee
    0.06
    Act Density 0.115%

    No Known Activations