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

    Neuronpedia

    INDEX
    Explanations

    adverbs and descriptive qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आदि
    0.32
     arasındaki
    0.30
     "/",
    0.28
     প্রমুখ
    0.26
     beserta
    0.26
    <0xE3>
    0.26
     सकुशल
    0.25
     "\
    0.25
     conducive
    0.25
     ‎
    0.25
    POSITIVE LOGITS
    ly
    0.67
    ভাবে
    0.60
     enough
    0.58
    하게
    0.50
     banget
    0.50
    पणे
    0.49
     ביותר
    0.48
     but
    0.48
    mente
    0.47
    ترین
    0.46
    Act Density 0.513%

    No Known Activations