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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Package
    -0.07
    Samples
    -0.06
     danger
    -0.06
    Item
    -0.06
    费用
    -0.06
    ி
    -0.06
     Prevention
    -0.06
    Contract
    -0.06
    Power
    -0.06
    行动
    -0.06
    POSITIVE LOGITS
    左
    0.06
     QtCore
    0.06
     köln
    0.06
    >i
    0.06
    .GL
    0.06
    angelo
    0.06
     října
    0.06
     Coastal
    0.06
     Đây
    0.06
     χωρίς
    0.06
    Act Density 0.010%

    No Known Activations