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

    Neuronpedia

    INDEX
    Explanations

    stunning physique

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    نيا
    0.48
    ülü
    0.46
    ủ
    0.46
    ük
    0.46
    irsi
    0.45
    üğü
    0.45
    )^{*}$
    0.45
    Bib
    0.44
    ớt
    0.44
    owska
    0.44
    POSITIVE LOGITS
    \
    0.46
     screenshots
    0.45
     unsatisfied
    0.45
    <i>
    0.45
     gorges
    0.45
    ,((
    0.45
     aggrieved
    0.45
     lingers
    0.44
     інших
    0.44
     other
    0.43
    Act Density 0.008%

    No Known Activations