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

    Neuronpedia

    INDEX
    Explanations

    NASCAR

    np_max-act · gemini-2.0-flash

    This neuron detects named entities, especially proper nouns for races, venues, teams, and organizations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    hin
    -0.07
     chooser
    -0.07
    亭
    -0.07
    ��
    -0.06
    (ver
    -0.06
    จร
    -0.06
    Syn
    -0.06
    dar
    -0.06
    EFR
    -0.06
    ्श
    -0.06
    POSITIVE LOGITS
     dirección
    0.06
    		
↵
↵
    0.06
     STEM
    0.06
    	
↵
    0.06
    §
    0.06
     SAMPLE
    0.06
    ç
    0.06
    [item
    0.06
     letter
    0.06
     месяца
    0.06
    Act Density 0.011%

    No Known Activations