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

    Neuronpedia

    INDEX
    Explanations

    Varanasi (Banaras)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    二级
    0.42
     بیاکت
    0.38
     Hertfordshire
    0.37
    Sophia
    0.37
    雅
    0.37
     Riyadh
    0.37
     गुरुग्राम
    0.36
     Kür
    0.36
     الكويت
    0.35
     snap
    0.35
    POSITIVE LOGITS
     Ban
    0.94
     Varanasi
    0.92
    Ban
    0.91
     वाराणसी
    0.86
     কাশী
    0.79
     Bana
    0.77
     काशी
    0.75
     BAN
    0.74
     Varan
    0.73
    BAN
    0.73
    Act Density 0.001%

    No Known Activations