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

    Neuronpedia

    INDEX
    Explanations

    good idea or choice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ome
    0.49
    un
    0.46
    riving
    0.45
    age
    0.45
    unc
    0.42
    og
    0.42
    ні
    0.42
    usc
    0.41
    helf
    0.41
    ofield
    0.41
    POSITIVE LOGITS
    InstrumentedTest
    0.44
    ཡ
    0.44
     financiación
    0.43
    相關文章
    0.43
     футболдук
    0.43
     kaleidos
    0.42
     bicovariant
    0.42
    <bbox>
    0.42
     idempot
    0.41
     bialgebras
    0.41
    Act Density 0.001%

    No Known Activations