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

    Neuronpedia

    INDEX
    Explanations

    _at

    np_max-act · gemini-2.0-flash

    The neuron activates on timestamp‐style schema fields—e.g. column names like “created_at,” “updated_at,” and other timestamp identifiers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    VD
    -0.07
    LED
    -0.07
    HECK
    -0.07
     organize
    -0.06
     FA
    -0.06
    uries
    -0.06
     tc
    -0.06
    ,'#
    -0.06
    ческим
    -0.06
    ilege
    -0.06
    POSITIVE LOGITS
     createdAt
    0.08
     Ghana
    0.07
    updatedAt
    0.07
    .createdAt
    0.07
     Patrick
    0.06
     accom
    0.06
     createDate
    0.06
    CreatedAt
    0.06
    UpdatedAt
    0.06
    at
    0.06
    Act Density 0.002%

    No Known Activations