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

    Neuronpedia

    INDEX
    Explanations

    humor and jokes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Synthesis
    0.81
    cosystem
    0.78
     പാല
    0.76
    缎
    0.73
     ઉત્પાદ
    0.73
    enthic
    0.72
    Chem
    0.72
     మార
    0.70
    Comprehensive
    0.70
    🛤
    0.69
    POSITIVE LOGITS
     humor
    3.88
     jokes
    3.87
     humorous
    3.86
     comedic
    3.77
     joke
    3.77
     comedy
    3.67
     hilarious
    3.64
     humour
    3.51
     comical
    3.38
     funny
    3.37
    Act Density 0.846%

    No Known Activations