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

    Neuronpedia

    INDEX
    Explanations

    bra-ket notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.93
    а
    0.86
    ש
    0.83
    у
    0.76
    <0x0D>
    0.75
    </strong>
    0.73
    r
    0.73
    ی
    0.73
    \
    0.72
    oc
    0.70
    POSITIVE LOGITS
     of
    0.80
    ຂອງ
    0.72
     هستند
    0.70
    𝚈
    0.65
    𝑭
    0.64
    𝗩
    0.64
    KET
    0.64
    are
    0.62
    oules
    0.62
    ЗИ
    0.62
    Act Density 0.000%

    No Known Activations