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

    Neuronpedia

    INDEX
    Explanations

    Center for names of places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.45
    impl
    0.42
    tropical
    0.41
     ट्रॉपिकल
    0.41
    datal
    0.39
    d
    0.39
    toh
    0.39
    侗
    0.38
     highland
    0.38
    oasis
    0.38
    POSITIVE LOGITS
     pedals
    0.42
    นด์
    0.42
     Ста
    0.41
     চেয়ারম্যান
    0.40
    caire
    0.40
     uiteindelijk
    0.40
    齊
    0.40
     monde
    0.38
     chairperson
    0.38
    邹
    0.38
    Act Density 0.004%

    No Known Activations