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

    Neuronpedia

    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash

    The neuron fires on personal names (author names) in academic references and bibliographic citations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     het
    -0.07
     machine
    -0.06
    bucket
    -0.06
     tỏ
    -0.06
     ecology
    -0.06
    Integration
    -0.06
     powder
    -0.06
     můžete
    -0.06
     whistle
    -0.06
    ANDLE
    -0.06
    POSITIVE LOGITS
     rely
    0.07
    .'↵↵
    0.07
    ")(
    0.07
    (BASE
    0.06
     researched
    0.06
    .lists
    0.06
    इसक
    0.06
    (sess
    0.06
    .Q
    0.06
    	new
    0.06
    Act Density 0.018%

    No Known Activations