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

    Neuronpedia

    INDEX
    Explanations

    corruption and money laundering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    但是如果
    -0.07
     skips
    -0.07
    igraph
    -0.07
    でした
    -0.07
    財
    -0.07
     current
    -0.07
    �
    -0.07
     enlightened
    -0.07
    넵
    -0.07
    Un
    -0.07
    POSITIVE LOGITS
    ABB
    0.08
     aboard
    0.07
    Bars
    0.07
     institute
    0.07
    (detail
    0.07
    密码
    0.07
    ApiKey
    0.07
    死
    0.07
    ocide
    0.07
    麂
    0.07
    Act Density 0.031%

    No Known Activations