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

    Neuronpedia

    INDEX
    Explanations

    one word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     livres
    2.48
    이
    2.42
     बीच
    2.28
     deities
    2.26
    करी
    2.24
    祺
    2.23
    istration
    2.23
    本セット
    2.23
     ilang
    2.19
    要
    2.17
    POSITIVE LOGITS
    st
    4.06
    ங்கிணை
    3.54
    ⃙
    3.40
    р
    3.23
    ️⃣
    3.14
    যোগে
    3.09
    dbjc
    3.05
    \!\
    3.04
    z
    2.98
    xbet
    2.77
    Act Density 0.679%

    No Known Activations