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

    Neuronpedia

    INDEX
    Explanations

    ing

    np_max-act · gemini-2.0-flash

    The neuron fires strongly on present‐participle or gerund verbs ending in “-ing” that describe actions (e.g. “turning,” “opening,” “putting,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Equal
    -0.07
     sẽ
    -0.07
    Locker
    -0.07
     carbon
    -0.06
    (withDuration
    -0.06
     Wei
    -0.06
    Geom
    -0.06
    stringValue
    -0.06
    _word
    -0.06
     ToString
    -0.06
    POSITIVE LOGITS
    kb
    0.07
     khu
    0.06
     Winnipeg
    0.06
    book
    0.06
     Camb
    0.06
     çarp
    0.06
    _AD
    0.06
    UGHT
    0.06
     خوبی
    0.06
    advert
    0.06
    Act Density 0.052%

    No Known Activations