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

    Neuronpedia

    INDEX
    Explanations

    as possible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )<
    0.53
    นี้
    0.48
    ).
    0.43
    ‌ی
    0.42
     as
    0.42
     яка
    0.42
     також
    0.41
    ों
    0.41
     जिसे
    0.40
     нас
    0.40
    POSITIVE LOGITS
    in
    0.64
    at
    0.63
    i
    0.61
    an
    0.61
    il
    0.56
    er
    0.52
    י
    0.51
    ي
    0.48
    c
    0.46
    तः
    0.45
    Act Density 0.026%

    No Known Activations