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

    Neuronpedia

    INDEX
    Explanations

    let me know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     समझने
    0.41
     فهم
    0.37
     Familiar
    0.36
     Nanjing
    0.36
     समझ
    0.36
     familiar
    0.35
     Busan
    0.35
     understood
    0.34
     Doming
    0.33
    BLIC
    0.33
    POSITIVE LOGITS
     know
    0.74
    know
    0.65
    Know
    0.62
     знаю
    0.61
     Know
    0.60
    知
    0.60
     weten
    0.58
    知道
    0.57
     biết
    0.56
     wissen
    0.55
    Act Density 0.012%

    No Known Activations