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

    Neuronpedia

    INDEX
    Explanations

    thorough explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    os
    1.09
     on
    1.03
     În
    1.03
    ia
    1.00
     Neo
    1.00
    as
    0.94
     On
    0.92
    ur
    0.91
    c
    0.91
     Internal
    0.90
    POSITIVE LOGITS
    ми
    1.17
    ों
    1.00
    ки
    1.00
    юк
    0.96
    (
    0.96
    ६
    0.96
    ли
    0.95
    ных
    0.94
    اي
    0.93
     públicos
    0.92
    Act Density 0.008%

    No Known Activations