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

    Neuronpedia

    INDEX
    Explanations

    shakespearean english

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᓲ
    0.55
    ᙱ
    0.54
     максимально
    0.53
    鉭
    0.53
    ⴰ
    0.52
    ᠢ
    0.52
     تطبيقات
    0.51
     squiggle
    0.50
    謖
    0.49
    櫸
    0.48
    POSITIVE LOGITS
     doth
    0.76
     hath
    0.75
     certaine
    0.70
    ſ
    0.69
     tyme
    0.69
     shew
    0.65
     ſ
    0.63
     hadde
    0.61
     melancholy
    0.59
     thy
    0.58
    Act Density 0.006%

    No Known Activations