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

    Neuronpedia

    INDEX
    Explanations

    far-reaching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    0.99
     반
    0.93
    فين
    0.88
     Skyline
    0.87
    ה
    0.86
     Contrary
    0.86
     flip
    0.83
     residency
    0.83
    Concini
    0.81
    요
    0.80
    POSITIVE LOGITS
     flung
    1.39
    fetched
    1.38
    ্স্ট
    1.33
     fetched
    1.30
     afield
    1.29
    reaching
    1.29
     sighted
    1.08
     superior
    1.01
    ль
    1.00
     reaches
    1.00
    Act Density 0.058%

    No Known Activations