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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    instructions for securely managing sensitive information in programming environments.

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

    The neuron is strongly activated by common clause-linking discourse markers (especially “and,” “then,” “but,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ren
    -0.07
     Ok
    -0.07
    (filename
    -0.06
    (filePath
    -0.06
     converted
    -0.06
    (N
    -0.06
     internally
    -0.06
    itched
    -0.06
    Id
    -0.06
    (md
    -0.06
    POSITIVE LOGITS
    .bpm
    0.06
     VStack
    0.06
    _Customer
    0.06
    fit
    0.06
    bucks
    0.06
    Coffee
    0.06
    .twimg
    0.06
    .classList
    0.06
    ponder
    0.06
     diện
    0.06
    Act Density 0.115%

    No Known Activations