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

    Neuronpedia

    INDEX
    Explanations

    logic puzzles and riddles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ρο
    0.80
    旻
    0.76
     ホ
    0.73
     TR
    0.66
    どれ
    0.65
     আইনে
    0.64
    केश
    0.64
    憬
    0.64
     output
    0.64
     oike
    0.64
    POSITIVE LOGITS
     cento
    0.70
    Grunt
    0.67
     дверей
    0.63
    زی
    0.63
     সমাধিতে
    0.62
     }%
    0.61
    त्न
    0.60
     hewan
    0.60
    สัตว์
    0.60
     gra
    0.60
    Act Density 0.001%

    No Known Activations