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

    Neuronpedia

    INDEX
    Explanations

    pond, water

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mux
    -0.09
     multiplex
    -0.08
     knitting
    -0.08
     Social
    -0.08
     SELL
    -0.07
    fehl
    -0.07
     coefficient
    -0.07
     multicast
    -0.07
     Directed
    -0.07
     экспорт
    -0.07
    POSITIVE LOGITS
    浴
    0.10
    _bucket
    0.09
     cómod
    0.09
     cómoda
    0.09
    _members
    0.08
     cómodo
    0.08
    Membership
    0.08
    살
    0.08
    艇
    0.08
     comfy
    0.08
    Act Density 0.011%

    No Known Activations