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

    Neuronpedia

    INDEX
    Explanations

    clause, limitations, limits, verified

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !";
    1.31
     }}$.
    1.27
    !”.
    1.23
    。\
    1.23
    .";
    1.21
    .';
    1.19
    。.
    1.18
    ’।
    1.17
    "/>.
    1.17
    }^{*}$.
    1.15
    POSITIVE LOGITS
     there
    2.25
     it
    1.87
     they
    1.82
     فإن
    1.72
    there
    1.57
     you
    1.56
     thì
    1.48
     these
    1.47
     we
    1.41
     theres
    1.40
    Act Density 0.382%

    No Known Activations