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

    place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.58
    kiel
    -0.55
     محفوظة
    -0.54
    ///</
    -0.54
    protoimpl
    -0.52
    Rohy
    -0.52
    contentLoaded
    -0.50
     springfox
    -0.49
     propOrder
    -0.49
    posables
    -0.48
    POSITIVE LOGITS
     town
    0.82
     ciudad
    0.66
     Town
    0.66
     şehir
    0.59
     city
    0.57
     village
    0.56
     město
    0.54
    Town
    0.54
     towns
    0.52
     City
    0.51
    Act Density 0.047%

    No Known Activations