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

    Neuronpedia

    INDEX
    Explanations

    mathematical or scientific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𐰆
    0.41
     Коро
    0.40
    bungen
    0.39
     crown
    0.38
    myButtons
    0.38
    crown
    0.38
    ரஜன்
    0.38
    CurrentImage
    0.38
    appList
    0.38
     مۇ
    0.38
    POSITIVE LOGITS
    이제
    0.41
     широкий
    0.40
     ≤
    0.38
     ✅
    0.36
     silice
    0.36
     이제
    0.35
     DOM
    0.35
     now
    0.35
     Jetzt
    0.35
     DG
    0.35
    Act Density 0.027%

    No Known Activations