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

    Neuronpedia

    INDEX
    Explanations

    holidays and celebrations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Akhtar
    0.87
     მოს
    0.79
     contatt
    0.78
     agile
    0.75
     reliable
    0.75
     विश्वसनीय
    0.74
    痧
    0.73
     ওয়াস
    0.73
     folds
    0.72
     trusted
    0.72
    POSITIVE LOGITS
     celebration
    2.23
     anniversary
    2.18
     celebrations
    2.16
     birthday
    1.98
     holiday
    1.90
     Anniversary
    1.88
     Celebration
    1.88
     celebratory
    1.88
     celebrate
    1.86
     celebrating
    1.86
    Act Density 0.479%

    No Known Activations