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

    Neuronpedia

    INDEX
    Explanations

    transportation

    np_max-act · gemini-2.0-flash

    This neuron responds whenever it sees an “-ing” suffix—i.e. it detects gerund or present‐participle word endings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ани
    -0.06
     Nathan
    -0.06
    fifo
    -0.06
     rừng
    -0.06
    _OWNER
    -0.06
     lite
    -0.06
     stereotype
    -0.06
     додатков
    -0.06
    -len
    -0.06
     pairwise
    -0.06
    POSITIVE LOGITS
     />\
    0.07
     parcels
    0.07
    meyi
    0.07
     scenic
    0.06
    ıklı
    0.06
     prolong
    0.06
     Monkey
    0.06
    reement
    0.06
     حل
    0.06
    ací
    0.06
    Act Density 0.030%

    No Known Activations