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

    Neuronpedia

    INDEX
    Explanations

    genetic engineering/resistance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HomeAs
    -0.07
    特朗
    -0.07
     coordinated
    -0.06
    验收
    -0.06
    -too
    -0.06
    bose
    -0.06
    党史学习
    -0.06
    typ
    -0.06
    .Include
    -0.06
     Advanced
    -0.06
    POSITIVE LOGITS
     aquel
    0.08
    arket
    0.08
    低い
    0.07
     Basket
    0.07
     Essentials
    0.07
    わり
    0.07
     Crest
    0.07
    其他的
    0.07
     dudes
    0.07
    原来的
    0.07
    Act Density 0.012%

    No Known Activations