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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron primarily detects numeric tokens representing years or dates.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     practice
    -0.07
     gov
    -0.06
     tents
    -0.06
    (visitor
    -0.06
    Resistance
    -0.06
    орм
    -0.06
     @"
    -0.06
     Brent
    -0.06
    .gwt
    -0.06
     UserId
    -0.06
    POSITIVE LOGITS
    _DAYS
    0.06
     encompass
    0.06
    _tile
    0.06
     окра
    0.06
    込
    0.06
    _prepare
    0.06
    ilerden
    0.06
    ettel
    0.06
     لك
    0.06
    -lined
    0.06
    Act Density 0.036%

    No Known Activations