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

    Neuronpedia

    INDEX
    Explanations

    and or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     människor
    1.08
    <unused1879>
    1.04
     lidí
    0.99
     whatnot
    0.98
     ఇతర
    0.97
    <unused1728>
    0.96
     paljon
    0.95
    gür
    0.93
     município
    0.91
    <unused2126>
    0.91
    POSITIVE LOGITS
     (
    1.18
     and
    1.16
     (=
    1.10
     =
    1.08
     и
    1.00
     này
    0.99
     +
    0.95
    (
    0.95
     :
    0.95
     หรือ
    0.95
    Act Density 0.001%

    No Known Activations