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

    Neuronpedia

    INDEX
    Explanations

    specific dates and holidays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Half
    0.48
    Half
    0.42
     half
    0.41
    Landscape
    0.40
     landscape
    0.38
     Landscape
    0.38
    landscape
    0.38
     Halb
    0.38
    กฏ
    0.37
    上半
    0.37
    POSITIVE LOGITS
     holidays
    0.61
     वैलेंटाइन
    0.61
     Holidays
    0.59
     valentine
    0.50
     Valentine
    0.49
     Valentines
    0.49
     वैलेंट
    0.49
     birthday
    0.49
     valentines
    0.48
    Valentine
    0.48
    Act Density 0.000%

    No Known Activations