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

    Neuronpedia

    INDEX
    Explanations

    date placeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﭥ
    0.85
     siRNA
    0.84
     progenitor
    0.79
    닉
    0.76
    sklearn
    0.75
    منا
    0.75
    ive
    0.75
    এর
    0.74
     biaya
    0.74
    *}\
    0.72
    POSITIVE LOGITS
     tháng
    0.92
     واللي
    0.85
     जबकि
    0.85
    AndTime
    0.81
    cake
    0.78
    oh
    0.76
    ্পনিক
    0.75
    titulo
    0.75
     manner
    0.73
    लिटी
    0.72
    Act Density 0.131%

    No Known Activations