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

    Neuronpedia

    INDEX
    Explanations

    jokes and puns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     glorious
    0.40
     emergent
    0.40
     그대로
    0.38
    ಬಹುದ
    0.38
     emerges
    0.38
    로부터
    0.37
    固
    0.37
     inward
    0.36
     emerge
    0.36
     wondrous
    0.36
    POSITIVE LOGITS
     puns
    0.59
     jokes
    0.54
     joke
    0.50
    jokes
    0.49
    -',
    0.47
    joke
    0.46
     एनीमिया
    0.46
     Jokes
    0.44
     joked
    0.44
     ਰ
    0.43
    Act Density 0.119%

    No Known Activations