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

    Neuronpedia

    INDEX
    Explanations

    from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    そこに
    0.46
    డంలో
    0.43
    にかけて
    0.39
     거기에
    0.38
     ጋር
    0.36
    内に
    0.36
    पदी
    0.36
    면에
    0.36
     તેમાં
    0.36
    ছনে
    0.35
    POSITIVE LOGITS
     from
    3.86
    from
    3.70
    จาก
    3.42
     från
    3.30
     từ
    3.22
     από
    2.89
     kutoka
    2.88
     FROM
    2.86
     dari
    2.84
     от
    2.77
    Act Density 0.699%

    No Known Activations