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

    Neuronpedia

    INDEX
    Explanations

    some

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     लाखों
    0.69
     aDecoder
    0.65
     throughout
    0.65
     duquel
    0.63
    <unused383>
    0.62
    ប៉ុ
    0.60
    Burns
    0.60
    ifters
    0.60
     pandemics
    0.59
     अमन
    0.59
    POSITIVE LOGITS
     some
    2.80
     Some
    2.69
    some
    2.63
    Some
    2.60
     SOME
    2.59
    SOME
    2.36
     noen
    2.12
    一些
    2.06
     بعض
    2.05
     algunos
    1.99
    Act Density 0.266%

    No Known Activations