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

    Neuronpedia

    INDEX
    Explanations

    Tyvek, Ubuntu, Friends, artifacts, outright

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    0.98
    ع
    0.95
    ซ์
    0.94
     ناح
    0.92
    ма
    0.89
    น
    0.89
    عة
    0.88
     Defines
    0.88
    عت
    0.87
    لي
    0.86
    POSITIVE LOGITS
    ഘാ
    0.87
     decimos
    0.82
     stara
    0.81
    EventEmitter
    0.80
     cơn
    0.80
     गेल
    0.79
     Atención
    0.79
     hidrográf
    0.78
     equivariant
    0.78
    ות
    0.77
    Act Density 0.000%

    No Known Activations