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

    Neuronpedia

    INDEX
    Explanations

    software/applications/products

    np_max-act · gemini-2.0-flash

    This neuron does not activate for any tokens—it remains silent (zero) on all inputs.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     AFTER
    -0.07
     catalyst
    -0.06
     Respond
    -0.06
    ocide
    -0.06
    _attrs
    -0.06
    account
    -0.06
     blow
    -0.06
    ंधन
    -0.06
    nosti
    -0.06
    _started
    -0.06
    POSITIVE LOGITS
     dives
    0.06
    .yy
    0.06
     маш
    0.06
    sto
    0.06
     гал
    0.06
    _CAN
    0.06
    ikut
    0.06
    {id
    0.06
     headquartered
    0.06
    침
    0.06
    Act Density 0.035%

    No Known Activations