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

    Neuronpedia

    INDEX
    Explanations

    possibility or illustration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     niest
    0.44
    çe
    0.43
    прочем
    0.43
     tbh
    0.42
     сожалению
    0.41
    áll
    0.40
    基本的に
    0.40
    Either
    0.40
     특히
    0.40
    특히
    0.39
    POSITIVE LOGITS
     เงี้ย
    0.57
     مثلا
    0.53
    きっと
    0.48
     kanske
    0.47
     suddenly
    0.46
     might
    0.46
     magari
    0.46
    だったら
    0.46
    might
    0.45
     conceivably
    0.44
    Act Density 0.073%

    No Known Activations