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

    Neuronpedia

    INDEX
    Explanations

    particle usage in multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     была
    0.91
     बढ़े
    0.90
     worden
    0.88
     был
    0.85
     arrived
    0.84
    会被
    0.84
     شدم
    0.83
    就被
    0.82
     nincs
    0.82
     došlo
    0.82
    POSITIVE LOGITS
     만들
    1.03
    にする
    0.98
    にします
    0.94
     가지고
    0.89
     değişt
    0.89
     갖
    0.87
     anbieten
    0.86
     통해
    0.82
     కలిగి
    0.82
    上げる
    0.82
    Act Density 0.018%

    No Known Activations