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

    Neuronpedia

    INDEX
    Explanations

    Worcester

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     国产
    -0.07
     ue
    -0.07
    lew
    -0.07
    喜欢
    -0.07
    Rick
    -0.06
    Intensity
    -0.06
     индивиду
    -0.06
    时间
    -0.06
    샵
    -0.06
    films
    -0.06
    POSITIVE LOGITS
     Worcester
    0.29
     Wichita
    0.15
     Worce
    0.12
    ster
    0.08
    .urlopen
    0.08
     syslog
    0.07
     Norwich
    0.07
    ्यक
    0.06
     alertController
    0.06
     MCP
    0.06
    Act Density 0.001%

    No Known Activations