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

    Neuronpedia

    INDEX
    Explanations

    boots

    np_max-act · gemini-2.0-flash

    The neuron responds to capitalized named entities and proper nouns (e.g., brand names, titles, or specific place/person names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     reck
    -0.06
     obs
    -0.06
    	range
    -0.06
     Refresh
    -0.06
    isEqualTo
    -0.06
     color
    -0.06
     eclipse
    -0.06
     obten
    -0.06
     darling
    -0.06
     hunter
    -0.06
    POSITIVE LOGITS
    เกล
    0.07
     }

↵
    0.07
    奖
    0.07
    ┴
    0.06
    COMM
    0.06
     NotificationCenter
    0.06
    ?↵↵
    0.06
    <Role
    0.06
    tea
    0.06
    .fromCharCode
    0.06
    Act Density 0.120%

    No Known Activations