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

    Neuronpedia

    INDEX
    Explanations

    docker-compose versions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _production
    -0.07
     ConnectionState
    -0.07
     ReturnType
    -0.06
    Loads
    -0.06
     Sold
    -0.06
    inces
    -0.06
     Supplement
    -0.06
    .getType
    -0.06
    -example
    -0.06
    .shutdown
    -0.06
    POSITIVE LOGITS
    𨱇
    0.07
     owned
    0.07
    record
    0.07
    般的
    0.06
     кон
    0.06
     необходимо
    0.06
    imed
    0.06
     waiting
    0.06
     caused
    0.06
    行
    0.06
    Act Density 0.002%

    No Known Activations