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

    Neuronpedia

    INDEX
    Explanations

    goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    possibly
    0.46
    場合があります
    0.44
     धन्यवाद
    0.42
    netlify
    0.41
     território
    0.40
     spesso
    0.39
    ovali
    0.39
     ieri
    0.39
     awoke
    0.39
    often
    0.38
    POSITIVE LOGITS
     that
    0.54
     stamina
    0.48
     innervation
    0.46
    ส่ง
    0.45
     që
    0.43
     wszystkie
    0.42
     افزایش
    0.42
     wymaga
    0.41
    Henderson
    0.41
     وقتی
    0.41
    Act Density 0.009%

    No Known Activations