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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    loomberg
    -0.09
     bmp
    -0.07
     supplemental
    -0.07
    不锈
    -0.07
    ƺ
    -0.07
    stime
    -0.06
    lies
    -0.06
    曾任
    -0.06
    Elem
    -0.06
    COVID
    -0.06
    POSITIVE LOGITS
    .receiver
    0.09
     {"
    0.07
     ihtiy
    0.07
    꼭
    0.07
    期待
    0.07
    偷
    0.07
     ха
    0.07
    ימי
    0.07
     ба
    0.06
     ancestor
    0.06
    Act Density 0.003%

    No Known Activations