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

    Neuronpedia

    INDEX
    Explanations

    are, can, to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     was
    1.54
    was
    1.49
     Was
    1.44
    Was
    1.41
     WAS
    1.13
     wasn
    1.08
     Wasn
    1.00
     wasnt
    1.00
     રહ્યું
    0.91
     تھا۔
    0.87
    POSITIVE LOGITS
     đều
    3.63
    都
    3.28
     ovat
    3.19
    都有
    3.14
     هستند
    3.12
     estão
    3.10
    都能
    3.06
     possono
    3.05
     janë
    3.04
     are
    3.04
    Act Density 0.117%

    No Known Activations