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

    Neuronpedia

    INDEX
    Explanations

    greetings and inquiries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ƣ
    0.44
    ناء
    0.43
    Lorsque
    0.40
    Instituto
    0.38
    Tanh
    0.38
    ursing
    0.38
    ‣
    0.37
     Lorsque
    0.37
    ״
    0.37
    McC
    0.36
    POSITIVE LOGITS
     đc
    0.90
     cái
    0.83
     bạn
    0.75
     nè
    0.70
     đấy
    0.69
     mấy
    0.68
     nó
    0.66
     nhá
    0.66
     hơi
    0.65
     chỗ
    0.64
    Act Density 0.001%

    No Known Activations