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

    Neuronpedia

    INDEX
    Explanations

    which means explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    当然
    0.43
     конечно
    0.43
    ことになる
    0.42
    疑問
    0.42
    ধ্যে
    0.41
     synonymous
    0.39
     当然
    0.39
    Obviously
    0.39
     जाहिर
    0.39
    电线路
    0.39
    POSITIVE LOGITS
     distinguishes
    0.52
     sets
    0.49
     status
    0.48
     distinctions
    0.48
     distinguish
    0.46
     distinction
    0.46
     frees
    0.45
     자유
    0.43
     spezielle
    0.43
     Distinction
    0.43
    Act Density 0.016%

    No Known Activations