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

    Neuronpedia

    INDEX
    Explanations

    so much positivity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     или
    0.52
     ឬ
    0.52
    最も
    0.50
    或
    0.50
    分為
    0.49
     ወይም
    0.48
     hoặc
    0.47
    如果
    0.46
     зависимости
    0.45
     radically
    0.45
    POSITIVE LOGITS
     इतनी
    0.63
    这么多
    0.61
     столь
    0.60
    這麼
    0.59
     this
    0.59
     этом
    0.58
     इतने
    0.57
     această
    0.55
     هذا
    0.54
     kesempatan
    0.54
    Act Density 0.308%

    No Known Activations