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

    Neuronpedia

    INDEX
    Explanations

    sounds and mechanical actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     কারণেই
    0.49
     سواء
    0.46
    斯
    0.44
     প্রতিহিংস
    0.44
    战争
    0.43
    坞
    0.43
    梦想
    0.43
    晧
    0.43
    ডিএফ
    0.42
    Ꮡ
    0.42
    POSITIVE LOGITS
     faintly
    0.61
     is
    0.49
     intermittently
    0.46
     ngunit
    0.45
     emitted
    0.43
     but
    0.42
     weakly
    0.42
     atmósfera
    0.42
     gently
    0.42
     softly
    0.41
    Act Density 0.009%

    No Known Activations