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

    Neuronpedia

    INDEX
    Explanations

    expressing personal thoughts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     प्रदान
    0.43
     这里
    0.42
     नीड
    0.41
     odpow
    0.40
     この
    0.40
    淢
    0.39
     cần
    0.39
    irsi
    0.39
     этом
    0.39
    калә
    0.39
    POSITIVE LOGITS
     see
    0.44
     sieht
    0.43
     expected
    0.41
     expect
    0.39
     sees
    0.39
    เห็น
    0.39
     seeing
    0.38
     happening
    0.38
     seen
    0.37
     think
    0.37
    Act Density 0.111%

    No Known Activations