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

    Neuronpedia

    INDEX
    Explanations

    similarity and difference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    最好的
    0.98
     оптима
    0.96
     забезпечення
    0.96
     optimum
    0.95
    最好
    0.95
     unforgettable
    0.95
     обеспечения
    0.94
     tireless
    0.94
     optimally
    0.94
     optimal
    0.94
    POSITIVE LOGITS
     similar
    2.14
     비슷
    2.05
     comparable
    1.97
     similarly
    1.90
     Similar
    1.90
     identical
    1.87
     dezelfde
    1.86
     similarities
    1.85
    similar
    1.84
     similaire
    1.84
    Act Density 1.205%

    No Known Activations