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

    Neuronpedia

    INDEX
    Explanations

    dates and events

    np_max-act · gemini-2.0-flash

    The neuron activates on parts of date expressions—month names, day numbers, and year numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     заліз
    -0.06
    скому
    -0.06
     Latina
    -0.06
    enia
    -0.06
    ASET
    -0.06
     usually
    -0.06
    ustralian
    -0.06
    298
    -0.06
    olas
    -0.06
     ITE
    -0.06
    POSITIVE LOGITS
     merak
    0.07
    _classification
    0.07
     Announcement
    0.07
     Antique
    0.06
    Packet
    0.06
     піс
    0.06
     dieses
    0.06
     تش
    0.06
     salario
    0.06
     čá
    0.06
    Act Density 0.070%

    No Known Activations