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

    Neuronpedia

    INDEX
    Explanations

    "rejection", "contamination", "foaming"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    スト
    0.43
    たら
    0.39
     Orn
    0.39
    otal
    0.37
    可能性がある
    0.37
     elenc
    0.36
    amide
    0.36
     Rainbow
    0.35
    様子
    0.35
    ちゃん
    0.35
    POSITIVE LOGITS
    ícito
    0.40
    여기
    0.40
    挹
    0.39
     Cái
    0.39
     puris
    0.39
    rhe
    0.39
     여기서
    0.38
     rheumat
    0.38
     njemu
    0.38
     প্রদ
    0.37
    Act Density 0.000%

    No Known Activations