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
    �
    -0.06
    Content
    -0.06
     evac
    -0.06
     Foam
    -0.06
    zte
    -0.06
     positivity
    -0.06
    Path
    -0.06
    actical
    -0.06
     Putin
    -0.06
     Throws
    -0.06
    POSITIVE LOGITS
     serves
    0.13
     serve
    0.11
     served
    0.10
     serving
    0.10
     Serve
    0.09
     srv
    0.08
    -serving
    0.07
    _sr
    0.07
    며
    0.07
    slave
    0.07
    Act Density 0.016%

    No Known Activations