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

    Neuronpedia

    INDEX
    Explanations

    absurdity and ridiculousness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    torn
    0.43
    eek
    0.40
     tricky
    0.39
     型
    0.39
     څرنګ
    0.38
    Interesting
    0.38
    型
    0.38
     সমস্যায়
    0.37
    சிக்க
    0.37
    不好
    0.37
    POSITIVE LOGITS
     absurd
    1.09
     ridiculous
    1.06
     absurdity
    0.98
     absur
    0.89
     stupid
    0.89
     ludicrous
    0.88
     silly
    0.86
     foolish
    0.82
     nonsense
    0.82
     insane
    0.78
    Act Density 0.016%

    No Known Activations