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

    Neuronpedia

    INDEX
    Explanations

    rights

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .This
    -0.07
    䌹
    -0.07
    .Long
    -0.07
    节约
    -0.06
    绤
    -0.06
    .Binding
    -0.06
     field
    -0.06
    制定
    -0.06
    개발
    -0.06
     convicted
    -0.06
    POSITIVE LOGITS
    Defs
    0.07
    帮忙
    0.07
    灰色
    0.07
     flere
    0.07
    .getAs
    0.07
    ahkan
    0.07
     부분
    0.07
    emat
    0.07
    吊顶
    0.07
    컬
    0.07
    Act Density 0.001%

    No Known Activations