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

    Neuronpedia

    INDEX
    Explanations

    locations and finance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     اتھار
    0.45
    ธ์
    0.44
    maları
    0.43
    劭
    0.43
    kti
    0.42
    vpn
    0.41
    爯
    0.40
    тельной
    0.39
    颤
    0.39
    编码
    0.39
    POSITIVE LOGITS
     Alumni
    0.47
     I
    0.46
     money
    0.46
     Delta
    0.45
     alumni
    0.44
     donor
    0.44
     leftovers
    0.43
     Embassy
    0.43
     donors
    0.42
     contours
    0.42
    Act Density 0.084%

    No Known Activations