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

    Neuronpedia

    INDEX
    Explanations

    references to Tibetan culture and geography

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tibet or Tibetan

    np_acts-logits-general · gemini-2.0-flash

    Tibetan Plateau

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tonode
    -0.71
    الإنجليزية
    -0.63
    fromnode
    -0.61
     Gees
    -0.54
     Minerva
    -0.51
    expandindo
    -0.50
     Philist
    -0.50
     Sienna
    -0.50
     Muske
    -0.49
     Bany
    -0.49
    POSITIVE LOGITS
     Tibetan
    0.95
     Tibet
    0.83
    Tib
    0.73
     tibet
    0.70
     Karma
    0.67
     Ladakh
    0.67
     Lama
    0.65
     Rin
    0.62
     Dalai
    0.61
     sherpa
    0.60
    Act Density 0.049%

    No Known Activations