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

    Neuronpedia

    INDEX
    Explanations

    plagiarism

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of copying or plagiarism—that is, words indicating stolen ideas or intellectual‐property infringement.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     foot
    -0.07
     있었
    -0.06
    570
    -0.06
    .boost
    -0.06
    970
    -0.06
     spray
    -0.06
     robots
    -0.06
    _df
    -0.06
     Davies
    -0.06
    Adobe
    -0.06
    POSITIVE LOGITS
    paginate
    0.07
     doubly
    0.07
     اطل
    0.06
     dern
    0.06
    >J
    0.06
     folly
    0.06
    Editable
    0.06
    径
    0.06
     особи
    0.06
    'elle
    0.06
    Act Density 0.072%

    No Known Activations