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

    Neuronpedia

    INDEX
    Explanations

    AI answers and entertainment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Word
    0.38
    जिए
    0.37
    쥔
    0.36
    while
    0.36
    本文
    0.35
    Imp
    0.34
    십시오
    0.34
    पाई
    0.34
    Đ
    0.34
    ปก
    0.33
    POSITIVE LOGITS
     hữu
    0.53
     유
    0.49
    క్త
    0.42
    闲
    0.42
    쾌
    0.41
    瀧
    0.41
    용한
    0.40
     Tube
    0.40
    チューブ
    0.39
    유
    0.39
    Act Density 0.001%

    No Known Activations