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

    Neuronpedia

    INDEX
    Explanations

    references to geographic locations and organizational structures in industry contexts

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

    Location words after "in" or "throughout"

    np_acts-logits-general · gemini-2.0-flash

    geographical locations after 'in'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Haitian
    -0.63
     Etrus
    -0.62
     Berliner
    -0.58
     Algerian
    -0.57
     Macedonian
    -0.57
     Tasmanian
    -0.57
     Florentine
    -0.56
     Athenian
    -0.55
    Welsh
    -0.55
     Flinders
    -0.55
    POSITIVE LOGITS
     Europe
    1.13
     England
    1.04
     India
    1.02
     France
    0.98
     Britain
    0.94
     Australia
    0.93
     Canada
    0.93
     Japan
    0.91
     Germany
    0.91
     Italy
    0.91
    Act Density 0.575%

    No Known Activations