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

    Neuronpedia

    INDEX
    Explanations

    relative clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     большинства
    0.27
    uları
    0.25
     দুর্বল
    0.25
    嗯
    0.25
    ்தான்
    0.24
     unsurprisingly
    0.24
     وض
    0.24
     nếu
    0.24
    আপনি
    0.23
    迎来
    0.23
    POSITIVE LOGITS
     મળે
    0.29
     haunts
    0.27
     কিনা
    0.26
    रक
    0.26
     haunt
    0.26
     ලද
    0.26
     drifted
    0.25
    oping
    0.25
    россий
    0.25
     rua
    0.24
    Act Density 0.037%

    No Known Activations