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

    Neuronpedia

    INDEX
    Explanations

    alignments and residents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     توانائی
    0.43
     ಎಸ್
    0.41
     იაპ
    0.40
     የግ
    0.40
    orption
    0.40
     преодо
    0.40
     ধারণ
    0.40
     ধর
    0.39
    хран
    0.39
     않는
    0.39
    POSITIVE LOGITS
    जैसा
    0.44
    Un
    0.42
     lineups
    0.38
     Residents
    0.38
    कप
    0.38
     Resid
    0.38
     penduduk
    0.38
     berbentuk
    0.38
    सही
    0.38
    Align
    0.37
    Act Density 27.054%

    No Known Activations