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

    Neuronpedia

    INDEX
    Explanations

    to debate, audits, date, season

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     よう
    0.41
     Historic
    0.40
     пон
    0.39
    ᴍ
    0.39
    ᴘ
    0.39
    圧力
    0.39
     khỏe
    0.39
    волю
    0.38
     знаю
    0.38
    brellas
    0.38
    POSITIVE LOGITS
    uskan
    0.39
    yor
    0.38
    மான
    0.37
     अध्यक्षता
    0.36
    럇
    0.36
    ಲಿನ
    0.36
    yl
    0.36
     spitting
    0.36
     eint
    0.36
    swap
    0.35
    Act Density 0.000%

    No Known Activations