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

    Neuronpedia

    INDEX
    Explanations

    city and country names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     K
    1.20
     C
    1.18
     March
    1.16
    ”)
    1.16
     El
    1.15
    e
    1.15
     August
    1.14
     J
    1.13
     July
    1.13
    ін
    1.12
    POSITIVE LOGITS
     mappings
    1.04
     clínicas
    1.00
    ဌ
    1.00
    から
    0.97
    ሶች
    0.97
    ઞ
    0.97
    ructive
    0.96
    त्ती
    0.96
     collaborations
    0.96
    деа
    0.96
    Act Density 0.001%

    No Known Activations