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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    definitions and explanations of concepts related to data and technology.

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

    The neuron detects definitional language—phrases describing what something “is” or “refers to,” as in formal definitions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (`${
    -0.06
    Features
    -0.06
    ndo
    -0.06
    _uuid
    -0.06
    	total
    -0.06
    selected
    -0.06
    (record
    -0.06
     แล
    -0.06
     Tyson
    -0.06
    _misc
    -0.06
    POSITIVE LOGITS
     �
    0.07
     هم
    0.06
     kim
    0.06
    frei
    0.06
    香港
    0.06
    йн
    0.06
     creed
    0.06
     пись
    0.06
    广
    0.06
    يف
    0.06
    Act Density 0.080%

    No Known Activations