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

    Neuronpedia

    INDEX
    Explanations

    family

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ܢܐ
    2.23
    ق
    2.17
    را
    2.13
    ிகா
    2.02
    স
    1.96
     истины
    1.92
    ก็ตาม
    1.91
    žky
    1.90
    ซึ่ง
    1.87
    匮
    1.87
    POSITIVE LOGITS
    er
    2.84
    d
    2.30
    。
    2.27
    ।
    2.25
    ر
    2.16
    。\
    2.09
    amp
    1.99
    r
    1.97
    ek
    1.96
    undant
    1.89
    Act Density 0.165%

    No Known Activations