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

    Neuronpedia

    INDEX
    Explanations

    covering a range of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    да
    2.48
    نا
    2.06
    ت
    1.64
    지로
    1.63
    ки
    1.62
    лла
    1.61
    ش
    1.60
    지
    1.58
    ج
    1.56
    лна
    1.55
    POSITIVE LOGITS
    씌
    1.75
    1.70
     encompass
    1.65
    as
    1.60
    rel
    1.52
    eb
    1.52
    an
    1.49
    aw
    1.48
     apuestas
    1.48
    ைகளால்
    1.47
    Act Density 0.228%

    No Known Activations