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

    Neuronpedia

    INDEX
    Explanations

    award

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     elevation
    -0.09
    借贷
    -0.07
    PROPERTY
    -0.07
     paved
    -0.07
    (Runtime
    -0.07
    OnChange
    -0.07
    好朋友
    -0.06
    原型
    -0.06
    全球化
    -0.06
    Gateway
    -0.06
    POSITIVE LOGITS
    蟑
    0.07
     percentages
    0.07
    じ
    0.07
    lings
    0.07
    shima
    0.06
    crest
    0.06
     الصحة
    0.06
     working
    0.06
     surfaces
    0.06
     bulunduğu
    0.06
    Act Density 0.003%

    No Known Activations