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

    Neuronpedia

    INDEX
    Explanations

    geographical locations and place names

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

    city names like Honolulu and Anchorage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mérit
    -0.50
     borboleta
    -0.48
    baiki
    -0.47
     boyunca
    -0.45
     davran
    -0.44
     chré
    -0.44
     çik
    -0.43
     récup
    -0.42
     Verdad
    -0.42
     démocr
    -0.42
    POSITIVE LOGITS
     Honolulu
    2.00
    Honolulu
    1.68
     Oahu
    1.16
    olulu
    1.03
     Anchorage
    0.80
     Phuket
    0.80
    ULU
    0.68
     Lusaka
    0.68
     Tahiti
    0.65
    executeQuery
    0.63
    Act Density 0.000%

    No Known Activations