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

    Neuronpedia

    INDEX
    Explanations

    place names and geographical locations

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

    places and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    protoimpl
    -0.79
    OGND
    -0.71
     Seeder
    -0.66
     '\\;'
    -0.65
    ftagPool
    -0.63
    RTEE
    -0.62
    fjspx
    -0.61
     pinulongan
    -0.59
    IndentedString
    -0.56
     LUMP
    -0.56
    POSITIVE LOGITS
     Vergnügen
    0.40
    Acceso
    0.35
     rumahnya
    0.34
     Hauses
    0.33
     islas
    0.32
     exactamente
    0.32
     Gegend
    0.32
     posesión
    0.32
     Plätze
    0.32
     direttamente
    0.31
    Act Density 0.022%

    No Known Activations