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

    Neuronpedia

    INDEX
    Explanations

    geographical locations and descriptive data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bering
    0.48
    orang
    0.44
    BottomSheet
    0.43
     Alaska
    0.42
     köy
    0.42
    irk
    0.41
    orange
    0.41
     Inuit
    0.41
    Alaska
    0.40
     Alaskan
    0.39
    POSITIVE LOGITS
     EUR
    0.44
     Mahmoud
    0.40
     md
    0.39
     Mahmud
    0.38
    HEIM
    0.38
     Patriot
    0.37
    glial
    0.37
     inoculated
    0.37
     ቀ
    0.36
     Ferg
    0.36
    Act Density 0.004%

    No Known Activations