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

    Neuronpedia

    INDEX
    Explanations

    references to American individuals in various professions

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

    nationalities followed by roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.60
    expandindo
    -0.53
    Билгалдахарш
    -0.52
    Personensuche
    -0.52
    
    -0.49
    UserScript
    -0.47
    sizeCache
    -0.46
    UnusedPrivate
    -0.45
    Зноскі
    -0.45
    featureID
    -0.45
    POSITIVE LOGITS
    amerikanischer
    0.60
     American
    0.58
     Duits
    0.55
     amerikanischen
    0.54
     gezicht
    0.54
     deutscher
    0.53
     człowieka
    0.51
     Duitse
    0.50
    󠁢
    0.50
     achtergrond
    0.49
    Act Density 0.038%

    No Known Activations