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

    Neuronpedia

    INDEX
    Explanations

    Mentioning/Noticing

    np_max-act · gemini-2.0-flash

    This neuron detects authorial commentary or emphasis phrases (e.g. “It should be…,” “It should be noted,” “It should be emphasized”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    730
    -0.08
    sku
    -0.07
    142
    -0.06
    Rub
    -0.06
    "x
    -0.06
    "People
    -0.06
    accessToken
    -0.06
    cont
    -0.06
    Copy
    -0.06
    В
    -0.06
    POSITIVE LOGITS
     Emacs
    0.07
    .requires
    0.07
    -wise
    0.07
     pošk
    0.07
     سلامت
    0.06
    駅徒歩
    0.06
    .defaultValue
    0.06
     resultSet
    0.06
     Colomb
    0.06
    .filters
    0.06
    Act Density 0.024%

    No Known Activations