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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron is specially tuned to detect numeric expressions—years, measurements, statistics, or other numbers in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     by
    -0.06
    emb
    -0.06
    德
    -0.06
     amazed
    -0.06
    545
    -0.06
    avě
    -0.06
    Note
    -0.06
    small
    -0.06
    -temp
    -0.06
    ']}}</
    -0.06
    POSITIVE LOGITS
    transition
    0.07
    	Texture
    0.07
    (blank
    0.07
     siêu
    0.06
     هن
    0.06
    _serializer
    0.06
    _stream
    0.06
    restricted
    0.06
    .sound
    0.06
    ुन
    0.06
    Act Density 0.042%

    No Known Activations