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

    Neuronpedia

    INDEX
    Explanations

    East Asia, Eastern Europe, East Timor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    1.02
    6
    1.01
    ي
    0.96
    ير
    0.93
    л
    0.92
    ل
    0.91
    ம்
    0.89
    ومي
    0.85
    েন
    0.84
    كان
    0.83
    POSITIVE LOGITS
     (
    1.25
     the
    0.93
    em
    0.91
    ना
    0.91
     t
    0.87
    -
    0.86
    not
    0.85
    s
    0.84
    س
    0.81
    ս
    0.80
    Act Density 0.111%

    No Known Activations