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

    Neuronpedia

    INDEX
    Explanations

    sentence structure

    np_max-act · gemini-2.0-flash

    The neuron fires on numerical tokens—years, counts, percentages, and other digit‐based quantities.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Alfred
    -0.06
     требует
    -0.06
    ium
    -0.06
    Ticket
    -0.06
     Karl
    -0.06
    pr
    -0.06
    mj
    -0.06
     imaginary
    -0.06
     Bluetooth
    -0.06
    Mine
    -0.06
    POSITIVE LOGITS
     Outputs
    0.06
    .close
    0.06
     Teuchos
    0.06
    .fetchone
    0.06
     brill
    0.06
     PAGE
    0.06
    _print
    0.06
    _Pre
    0.06
     PATCH
    0.06
    =create
    0.06
    Act Density 0.247%

    No Known Activations