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

    Neuronpedia

    INDEX
    Explanations

    changing technology or improvements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    0.88
    6
    0.84
    </h2>
    0.79
    that
    0.78
    5
    0.76
    </h5>
    0.71
    4
    0.71
    of
    0.71
     are
    0.69
    </strong>
    0.67
    POSITIVE LOGITS
    ر
    1.20
    u
    0.91
    ו
    0.89
    л
    0.84
    o
    0.81
    ل
    0.79
    uia
    0.77
    tól
    0.77
    ar
    0.73
    in
    0.71
    Act Density 1.934%

    No Known Activations