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

    Neuronpedia

    INDEX
    Explanations

    weekend days

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    л
    2.98
    σεις
    2.92
    en
    2.92
    𝗲
    2.85
    (\
    2.83
    𝗵
    2.60
    ichni
    2.44
    жити
    2.36
    Ро
    2.28
    픈
    2.23
    POSITIVE LOGITS
    ように
    2.95
    ය
    2.92
    𝑡
    2.91
    ти
    2.89
    transfected
    2.84
    ット
    2.80
    ようになりました
    2.79
    зву
    2.76
    ตรฐาน
    2.68
    𝑟
    2.68
    Act Density 0.005%

    No Known Activations