BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pycon-lithuania-2026//speaker//YC3XMF
BEGIN:VTIMEZONE
TZID:EET
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1;UNTIL=20011231T220000Z
TZNAME:EET
TZOFFSETFROM:+0200
TZOFFSETTO:+0200
END:STANDARD
BEGIN:STANDARD
DTSTART:20031026T050000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:EET
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20030330T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:EEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-pycon-lithuania-2026-KK9GKJ@pretalx.com
DTSTART;TZID=EET:20260410T120000
DTEND;TZID=EET:20260410T123000
DESCRIPTION:In this talk\, I propose to discuss the problem of building exp
 lainable AI with the two approaches - causal vs correlational. I will talk
  about what mech interp in LLMs. As a way to understand how models answer 
 questions by looking inside them and checking which neurons activate when.
  I will discuss Anthropic's open sourced a python module - circuit-tracer\
 , the Neuronpedia portal \, will also talk about my own work with "activat
 ion cube" data structure (this is not a standard - I came up with it)
DTSTAMP:20260619T081806Z
LOCATION:Krantas/Shore 213 (3rd building)
SUMMARY:XAI - Explainable AI tools and techniques - Viraj Sharma
URL:https://pretalx.com/pycon-lithuania-2026/talk/KK9GKJ/
END:VEVENT
END:VCALENDAR