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

    Neuronpedia

    INDEX
    Explanations

    connections between geographical locations and trade routes

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

    routes and directions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     acompan
    -0.32
    idados
    -0.31
     precies
    -0.30
     saját
    -0.30
     slightly
    -0.30
     exactement
    -0.30
    lijken
    -0.30
     category
    -0.30
     slight
    -0.30
     personal
    -0.30
    POSITIVE LOGITS
     destinations
    0.89
     EconPapers
    0.76
     westward
    0.73
     eastward
    0.69
     southward
    0.69
     disambiguazione
    0.69
     ligiloj
    0.65
    destinations
    0.65
     onward
    0.65
     destination
    0.64
    Act Density 0.042%

    No Known Activations