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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     storia
    -0.07
    撤
    -0.07
     Attributes
    -0.07
     intersect
    -0.07
     Split
    -0.07
    /(
    -0.07
    \Middleware
    -0.07
     pri
    -0.07
    ＜
    -0.06
     Convert
    -0.06
    POSITIVE LOGITS
    얌
    0.07
    柈
    0.07
     Abrams
    0.07
    偏向
    0.07
    .layers
    0.07
    ETS
    0.07
    多样
    0.07
    带头
    0.06
    管家
    0.06
    矬
    0.06
    Act Density 0.001%

    No Known Activations