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

    Neuronpedia

    INDEX
    Explanations

    previously mentioned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ალური
    0.62
    नक
    0.62
    жня
    0.57
    ൂടെ
    0.56
    льного
    0.55
    ൃത്ത
    0.54
    ባቢ
    0.54
    尔
    0.53
    cha
    0.53
    下
    0.53
    POSITIVE LOGITS
     above
    4.71
    above
    4.06
    上述
    3.85
     Above
    3.75
     aforementioned
    3.62
    Above
    3.56
    上記
    3.53
    上記の
    3.48
     acima
    3.45
     ABOVE
    3.35
    Act Density 0.645%

    No Known Activations