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

    Neuronpedia

    INDEX
    Explanations

    suffixes

    np_max-act · gemini-2.0-flash

    This neuron primarily detects words ending with the “-ing” suffix (present participles/gerunds).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     coloured
    -0.06
     hộp
    -0.06
     ros
    -0.06
    	check
    -0.06
    。你
    -0.06
    VK
    -0.06
    iyas
    -0.06
     सबस
    -0.06
     세상
    -0.06
     Beet
    -0.06
    POSITIVE LOGITS
    )set
    0.07
    _serialize
    0.07
    737
    0.07
     "'",
    0.07
    TURE
    0.06
    Incoming
    0.06
    -gallery
    0.06
     rents
    0.06
     anzeigen
    0.06
    omentum
    0.06
    Act Density 0.001%

    No Known Activations