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

    Neuronpedia

    INDEX
    Explanations

    following "below"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (?)
    0.47
    (?)
    0.44
     mengurangi
    0.44
     Tyr
    0.43
     elle
    0.42
     menghindari
    0.42
     dianggap
    0.41
     sfrutt
    0.41
     fortuit
    0.41
    <?>
    0.41
    POSITIVE LOGITS
    detailed
    0.47
    ordelen
    0.47
    ка
    0.47
    olja
    0.46
    анали
    0.46
    ുകളും
    0.46
     nämlich
    0.45
    antwort
    0.45
    👇
    0.45
     worksheets
    0.44
    Act Density 0.002%

    No Known Activations