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

    Neuronpedia

    INDEX
    Explanations

    names of places, particularly geographical locations and capitals

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

    city names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.77
    EndGlobalSection
    -0.71
    webElementXpaths
    -0.68
    enderror
    -0.68
    ValueStyle
    -0.63
    #+#
    -0.61
     Италијани
    -0.57
    AddTagHelper
    -0.57
    SharedCtor
    -0.56
     HasFactory
    -0.56
    POSITIVE LOGITS
    gucigalpa
    0.77
    lamabad
    0.74
    opje
    0.66
    wahati
    0.62
     Ababa
    0.60
     Kabul
    0.60
     Penh
    0.57
    mandu
    0.57
     Islamabad
    0.57
     Pyongyang
    0.56
    Act Density 0.027%

    No Known Activations