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

    Neuronpedia

    INDEX
    Explanations

    density measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Аб
    -0.07
    欢
    -0.06
    InitStruct
    -0.06
     billion
    -0.06
    Crypto
    -0.06
     Atomic
    -0.06
     choir
    -0.06
    -0.06
    .Unsupported
    -0.06
    -0.06
    POSITIVE LOGITS
    	trigger
    0.07
     경기도
    0.06
    ejte
    0.06
    <script
    0.06
    jure
    0.06
     phân
    0.06
    翻
    0.06
     podnik
    0.06
     demand
    0.06
     zaměř
    0.06
    Act Density 0.201%

    No Known Activations