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

    Neuronpedia

    INDEX
    Explanations

    references to urban locations and infrastructure

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

    "downtown"

    np_acts-logits-general · gemini-2.0-flash

    downtown areas and streets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Turquía
    -0.63
    httphttps
    -0.63
     '\\;'
    -0.61
     nahilalakip
    -0.61
     Bekasi
    -0.59
    aarrggbb
    -0.59
     surla
    -0.56
    цезда
    -0.56
    tanleria
    -0.54
    orghini
    -0.54
    POSITIVE LOGITS
     downtown
    0.84
     Downtown
    0.75
    Downtown
    0.70
    downtown
    0.69
     street
    0.56
     Street
    0.56
    street
    0.49
    Street
    0.47
     Square
    0.46
    streets
    0.42
    Act Density 0.135%

    No Known Activations