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

    Neuronpedia

    INDEX
    Explanations

    thank you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     desirable
    0.80
     zwią
    0.79
     hét
    0.75
    웨어
    0.74
    தை
    0.74
    অর্
    0.73
    要想
    0.73
     costitu
    0.72
    اث
    0.71
     akár
    0.71
    POSITIVE LOGITS
     alot
    1.52
    giving
    1.39
    givings
    1.31
     beaucoup
    1.29
     🙏
    1.25
     gracias
    1.17
     mucho
    1.12
     heaps
    1.12
     profusely
    1.10
     paljon
    1.10
    Act Density 0.025%

    No Known Activations