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

    Neuronpedia

    INDEX
    Explanations

    worn objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CurrentByte
    0.52
    얄
    0.48
     단순히
    0.47
     utilizes
    0.44
     simplistic
    0.44
     greatness
    0.43
     certain
    0.42
     the
    0.42
     countless
    0.42
    ियमित
    0.42
    POSITIVE LOGITS
    in
    0.57
    desde
    0.53
    和一个
    0.53
     desde
    0.52
     стоимо
    0.50
     from
    0.48
    as
    0.48
     ซึ่ง
    0.47
     appartenant
    0.47
     från
    0.46
    Act Density 0.009%

    No Known Activations