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

    Neuronpedia

    INDEX
    Explanations

    references to annual events or holidays

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "December", "November", or "Xmas"

    np_acts-logits-general · gemini-2.0-flash

    December and Christmas holidays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     summer
    -1.03
    SUMMER
    -1.00
    June
    -0.97
     June
    -0.97
    Summer
    -0.96
    summer
    -0.95
     Summer
    -0.95
     JUNE
    -0.91
     SUMMER
    -0.91
     summers
    -0.90
    POSITIVE LOGITS
     Christmas
    1.59
    Christmas
    1.50
     CHRISTMAS
    1.44
    christmas
    1.41
     December
    1.41
     christmas
    1.36
    December
    1.33
     Xmas
    1.31
     DECEMBER
    1.30
     xmas
    1.23
    Act Density 0.193%

    No Known Activations