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

    Neuronpedia

    INDEX
    Explanations

    synd

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xe
    -0.07
     victories
    -0.07
     lombok
    -0.07
    .stereotype
    -0.07
     đời
    -0.07
     thoải
    -0.07
    .init
    -0.07
    če
    -0.07
    秋天
    -0.06
    cheon
    -0.06
    POSITIVE LOGITS
    힐
    0.07
    护
    0.07
    ひと
    0.07
    垫
    0.07
    ');?></
    0.06
    '){
↵
    0.06
    工
    0.06
    )\↵
    0.06
     queryset
    0.06
    总有
    0.06
    Act Density 0.003%

    No Known Activations