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

    Neuronpedia

    INDEX
    Explanations

    geographical descriptors related to regions and directions

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

    compass directions and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.71
     kasarigan
    -0.69
    참고
    -0.63
     للمعارف
    -0.62
    UrlResolution
    -0.60
    pala
    -0.59
    DataAnnotations
    -0.59
     nahilalakip
    -0.58
    adpleegd
    -0.57
    ftagPool
    -0.56
    POSITIVE LOGITS
     east
    0.52
     eastern
    0.47
     avanzar
    0.40
     öst
    0.40
     eastward
    0.39
     west
    0.39
    eastern
    0.38
     western
    0.37
     selatan
    0.36
     Süden
    0.36
    Act Density 0.038%

    No Known Activations