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

    Neuronpedia

    INDEX
    Explanations

    russian language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     امید
    0.49
    Dividend
    0.48
    ከል
    0.47
     ответственности
    0.44
    Javascript
    0.44
    ्युअर
    0.44
     비교
    0.43
    Ladies
    0.43
    삭
    0.43
     l
    0.43
    POSITIVE LOGITS
     simili
    0.53
     simile
    0.52
     operador
    0.51
     roommate
    0.50
    megaphone
    0.50
    ഇ
    0.50
    achio
    0.49
     Igbo
    0.48
    ällä
    0.48
    imos
    0.48
    Act Density 0.001%

    No Known Activations