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

    Neuronpedia

    INDEX
    Explanations

    references to downtown locations and significant buildings

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

    urban central locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.47
     granja
    -0.46
    tanleria
    -0.46
    TypedDataSet
    -0.45
     countryside
    -0.44
     rancho
    -0.44
    évaluateur
    -0.43
     '\\;'
    -0.43
    ungalows
    -0.42
    Хьажоргаш
    -0.41
    POSITIVE LOGITS
     downtown
    0.93
     Downtown
    0.85
    Downtown
    0.83
    downtown
    0.75
     Innenstadt
    0.70
     central
    0.54
     city
    0.52
     City
    0.50
     centrally
    0.48
     Plaza
    0.47
    Act Density 0.075%

    No Known Activations