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

    Neuronpedia

    INDEX
    Explanations

    AI context and analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    อร์
    1.56
     séqu
    1.50
     conductas
    1.45
     policías
    1.45
     jueces
    1.44
    "،
    1.42
     préparations
    1.41
    स्कृतिक
    1.39
     grabado
    1.39
    醛
    1.38
    POSITIVE LOGITS
    at
    1.88
    et
    1.86
     the
    1.70
    ,
    1.70
    in
    1.66
    b
    1.56
    ק
    1.52
    it
    1.51
    িন
    1.50
     a
    1.47
    Act Density 0.318%

    No Known Activations