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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts and existence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     معمول
    0.31
     hjälp
    0.31
     예상
    0.30
     σημαν
    0.30
     vigt
    0.29
     vikt
    0.29
     ہفت
    0.29
     ویڈیو
    0.29
     belangrijke
    0.29
     awfully
    0.29
    POSITIVE LOGITS
     itself
    0.34
    bound
    0.30
    defined
    0.29
     convertView
    0.29
     resides
    0.29
    immersive
    0.29
    ின்
    0.28
     insanın
    0.28
    ણી
    0.26
     residing
    0.26
    Act Density 0.263%

    No Known Activations