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

    Neuronpedia

    INDEX
    Explanations

    formal writing

    np_max-act · gemini-2.0-flash

    The neuron fires on instructional, “how-to” style passages—especially where the assistant uses second-person imperatives (e.g. “you can…,” “to add…”) to explain or guide.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     hitter
    -0.07
    Colorado
    -0.07
     queryString
    -0.07
    IFEST
    -0.06
     Extremely
    -0.06
    Deleting
    -0.06
     وضع
    -0.06
     valore
    -0.06
    InternalServerError
    -0.06
     penet
    -0.06
    POSITIVE LOGITS
    _pdu
    0.07
    _good
    0.07
     exceptionally
    0.06
    odí
    0.06
     mái
    0.06
    ايت
    0.06
     nově
    0.06
    尔
    0.06
    Wars
    0.06
     ту
    0.06
    Act Density 0.678%

    No Known Activations