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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens that represent years or dates in historical contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Fever
    -0.07
     CEL
    -0.07
    _address
    -0.07
     Bounds
    -0.07
    (Card
    -0.06
    .ball
    -0.06
    (pkt
    -0.06
     esas
    -0.06
     京
    -0.06
     Mosque
    -0.06
    POSITIVE LOGITS
    دانلود
    0.07
     encountering
    0.07
    _colour
    0.06
    _triggered
    0.06
    ##
    0.06
    063
    0.06
    qb
    0.06
     nons
    0.06
     Petit
    0.06
    "},"
    0.06
    Act Density 0.022%

    No Known Activations