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

    Neuronpedia

    INDEX
    Explanations

    stalling, stack, stg

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    1.21
    2
    0.99
    6
    0.94
    ள்
    0.94
    5
    0.93
    ها
    0.86
    9
    0.84
    هاي
    0.79
    ุ
    0.77
    spiration
    0.75
    POSITIVE LOGITS
     اسٹ
    0.86
     روی
    0.85
     출연
    0.83
     스트
    0.82
     ویب
    0.80
    یک
    0.79
     آئے
    0.78
     도시
    0.78
     striis
    0.77
     grava
    0.77
    Act Density 0.964%

    No Known Activations