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

    Neuronpedia

    INDEX
    Explanations

    contrasting qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    而不是
    0.62
    不像
    0.51
     rather
    0.46
    而非
    0.46
     Bukan
    0.46
     bukan
    0.44
    のではなく
    0.44
    Unlike
    0.43
     Rather
    0.42
    ではなく
    0.42
    POSITIVE LOGITS
     hingegen
    0.62
     напротив
    0.59
     dagegen
    0.58
     justru
    0.56
     наоборот
    0.54
     오히려
    0.51
     మాత్రం
    0.47
     चाहिँ
    0.46
     훨씬
    0.46
     juist
    0.46
    Act Density 0.198%

    No Known Activations