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

    Neuronpedia

    INDEX
    Explanations

    code and data analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     extran
    -0.09
     Jumbo
    -0.09
     Nude
    -0.08
    .pem
    -0.08
     Doggy
    -0.08
    aanut
    -0.08
    visi
    -0.08
     statue
    -0.08
     Cinnamon
    -0.08
     Weiterlesen
    -0.08
    POSITIVE LOGITS
     summarize
    0.09
     manipulation
    0.08
    hold
    0.08
     verh
    0.08
    Await
    0.07
     analysis
    0.07
    同比
    0.07
    verage
    0.07
     बस
    0.07
     বস
    0.07
    Act Density 0.002%

    No Known Activations