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

    Neuronpedia

    INDEX
    Explanations

    resident of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ق
    1.09
    し
    1.05
    ف
    1.05
    ج
    1.04
    د
    1.00
    ث
    0.98
    ص
    0.97
     hypothes
    0.96
    حاد
    0.95
    ح
    0.93
    POSITIVE LOGITS
    IN
    1.16
    il
    1.08
    ine
    1.05
    y
    1.04
    ry
    1.02
    resident
    0.99
    ra
    0.93
    residents
    0.91
    le
    0.89
    ය
    0.89
    Act Density 0.006%

    No Known Activations