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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash

    queries and prompts related to user assistance or capabilities.

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

    The main thing this neuron does is detect the “can … do” question pattern (e.g. “what can you do,” “what can I do …”) in user requests.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     still
    -0.07
     rumpe
    -0.07
     zřejmě
    -0.06
     explo
    -0.06
    (jsonPath
    -0.06
     مول
    -0.06
    		↵	↵
    -0.06
     الاع
    -0.06
     essentially
    -0.06
     cris
    -0.06
    POSITIVE LOGITS
    .getList
    0.07
     каш
    0.06
    <KeyValuePair
    0.06
    ети
    0.06
    .duration
    0.06
    \d
    0.06
    ціональ
    0.06
    нії
    0.06
    .sg
    0.06
    �
    0.06
    Act Density 0.019%

    No Known Activations