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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tip
    -0.07
    -wrapper
    -0.07
     hero
    -0.07
    聚集
    -0.07
     Http
    -0.06
    ation
    -0.06
    categoryId
    -0.06
     Birch
    -0.06
    PackageManager
    -0.06
     Specifically
    -0.06
    POSITIVE LOGITS
    个交易
    0.07
     '..',
    0.06
    .addColumn
    0.06
     rượ
    0.06
    rän
    0.06
    phabet
    0.06
    reds
    0.06
     Huntington
    0.06
     sacrifices
    0.06
     хорош
    0.06
    Act Density 0.000%

    No Known Activations