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

    Neuronpedia

    INDEX
    Explanations

    serve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     s
    -0.07
     detailed
    -0.06
    ."),
    -0.06
    дем
    -0.06
    plits
    -0.06
     substances
    -0.06
     Scripture
    -0.06
     fseek
    -0.06
     MSS
    -0.06
    ==↵
    -0.06
    POSITIVE LOGITS
     serve
    0.17
     Serve
    0.10
    Serve
    0.09
    叔
    0.07
     伊
    0.07
    ०
    0.07
    /blue
    0.06
     Bella
    0.06
    Includes
    0.06
    -tech
    0.06
    Act Density 0.007%

    No Known Activations