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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    formal instructions or guides for planning events.

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

    The neuron fires on those little technical/numeric specification bits in formal documents—things like form numbers, cut-off dates, customization options (engraving, barrel colour, accessories), and similar precise detail tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	grid
    -0.08
     crypto
    -0.07
    (arc
    -0.06
     tap
    -0.06
    ,k
    -0.06
    (org
    -0.06
    .verify
    -0.06
     satire
    -0.06
    spacer
    -0.06
     ongoing
    -0.06
    POSITIVE LOGITS
    (withId
    0.07
     Barr
    0.06
     χα
    0.06
    not
    0.06
     DataBase
    0.06
    ành
    0.06
    ินท
    0.06
     التي
    0.06
     наві
    0.06
    (Employee
    0.06
    Act Density 0.157%

    No Known Activations