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

    Neuronpedia

    INDEX
    Explanations

    professor titles and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    g
    0.75
    gll
    0.72
    tsprec
    0.65
     учи
    0.64
    gulation
    0.63
    abdomen
    0.63
    ا
    0.63
    h
    0.62
    awt
    0.62
    াহিয়া
    0.62
    POSITIVE LOGITS
    it
    1.00
    কে
    0.99
    us
    0.93
    에
    0.87
    ina
    0.84
    ão
    0.80
    น
    0.79
    은
    0.78
    ad
    0.78
     Prof
    0.78
    Act Density 0.001%

    No Known Activations