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

    Neuronpedia

    INDEX
    Explanations

    business and technology domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     misalnya
    0.86
     ­
    0.80
     مثلا
    0.80
    もので
    0.76
     kemarin
    0.75
     هذا
    0.75
     أو
    0.72
     কিংবা
    0.72
     있는데요
    0.72
     때문에
    0.72
    POSITIVE LOGITS
    ↵↵↵
    1.15
    ↵↵
    1.11
    ↵↵↵↵
    1.04
    +.
    1.02
     &
    1.01
    ↵↵↵↵↵
    1.00
    ）.
    0.94
    】.
    0.92
     $.
    0.87
    」。
    0.87
    Act Density 0.480%

    No Known Activations