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

    Neuronpedia

    INDEX
    Explanations

    page

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وعند
    1.81
     verificare
    1.66
    ް
    1.64
    檛
    1.64
    ᱚ
    1.63
     pourront
    1.62
    叒
    1.61
     posiad
    1.54
     podrás
    1.53
    <0xAC>
    1.51
    POSITIVE LOGITS
    ся
    1.88
    蚣
    1.88
    p
    1.78
    ষ্ঠ
    1.70
    ють
    1.69
    𝟘
    1.66
    х
    1.62
     touted
    1.59
     spongy
    1.56
    id
    1.55
    Act Density 0.000%

    No Known Activations