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

    Neuronpedia

    INDEX
    Explanations

    Russophobia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.99
    ки
    0.85
    н
    0.75
    en
    0.70
    et
    0.61
    and
    0.61
    n
    0.61
    AN
    0.57
    0.57
    quare
    0.56
    POSITIVE LOGITS
    ס
    0.93
    डी
    0.77
    .。
    0.73
    نامه
    0.69
    ิค
    0.67
     cả
    0.66
    ทั้ง
    0.66
     bądź
    0.66
    ט
    0.66
    ين
    0.65
    Act Density 0.000%

    No Known Activations