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

    Neuronpedia

    INDEX
    Explanations

    places and cities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     submitted
    0.52
    Submitted
    0.51
    SHOW
    0.49
     show
    0.48
    Show
    0.48
     shows
    0.48
     description
    0.47
    Hidden
    0.46
     explanation
    0.46
     reported
    0.46
    POSITIVE LOGITS
     Nairobi
    0.60
     Makati
    0.55
     Kenya
    0.55
     Johannesburg
    0.51
     Brisbane
    0.50
     Dubai
    0.50
     নয়াদ
    0.49
     Uganda
    0.48
     दुबई
    0.48
     Beirut
    0.48
    Act Density 0.000%

    No Known Activations