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

    Neuronpedia

    INDEX
    Explanations

    root vertex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deserunt
    0.39
     제가
    0.38
     দলিল
    0.36
    োগ্র
    0.36
     mengalami
    0.36
     tribunals
    0.35
     বিপ
    0.35
     جوہری
    0.35
    제가
    0.34
     carreras
    0.34
    POSITIVE LOGITS
     fácil
    0.44
     tip
    0.39
     Tip
    0.39
    miş
    0.39
     awe
    0.38
    nse
    0.38
     Tap
    0.38
    舞
    0.38
    Tap
    0.37
    রদ্ব
    0.37
    Act Density 0.004%

    No Known Activations