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

    Neuronpedia

    INDEX
    Explanations

    warranty void / implications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.59
    。
    0.54
     it
    0.52
    ",
    0.51
    。"
    0.51
    IDAY
    0.50
    al
    0.49
    the
    0.49
     Benin
    0.48
    an
    0.48
    POSITIVE LOGITS
    де
    0.55
     فار
    0.47
    اد
    0.46
     interiores
    0.44
    දි
    0.44
     و
    0.44
    وب
    0.44
    ի
    0.43
    EVEN
    0.43
    رة
    0.43
    Act Density 0.002%

    No Known Activations