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

    Neuronpedia

    INDEX
    Explanations

    expert

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cycle
    -0.07
    úmer
    -0.07
     positivity
    -0.07
     Ping
    -0.07
    /pay
    -0.07
     sla
    -0.06
     dilation
    -0.06
     Sự
    -0.06
     leth
    -0.06
    敷
    -0.06
    POSITIVE LOGITS
     expert
    0.10
    expert
    0.10
     experts
    0.09
     Experts
    0.08
     Expert
    0.07
    Expert
    0.07
    Experts
    0.07
     expertise
    0.07
    pro
    0.07
     too
    0.06
    Act Density 0.017%

    No Known Activations