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

    Neuronpedia

    INDEX
    Explanations

    Conventionally

    np_max-act · gemini-2.0-flash

    This neuron activates on the discourse cue “Conventionally,” flagging sections that introduce or describe conventional (prior‐art) methods.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     biologist
    -0.07
     rebounds
    -0.07
    /email
    -0.06
     Bour
    -0.06
     Preferences
    -0.06
     repo
    -0.06
     Punjab
    -0.06
     cob
    -0.06
    平方
    -0.06
     resulted
    -0.06
    POSITIVE LOGITS
    0.07
    seo
    0.07
    имер
    0.07
    الي
    0.06
    sn
    0.06
     Bankası
    0.06
    LIKELY
    0.06
    many
    0.06
    더
    0.06
    yk
    0.06
    Act Density 0.010%

    No Known Activations