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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     site
    -0.06
     худ
    -0.06
     Giles
    -0.06
     С
    -0.06
    Bounds
    -0.05
    ุบาล
    -0.05
    .fit
    -0.05
    Life
    -0.05
     옷
    -0.05
     garden
    -0.05
    POSITIVE LOGITS
     "__
    0.07
     WX
    0.07
    Reward
    0.07
    /stat
    0.07
     CGI
    0.07
    LayoutManager
    0.07
     chlorine
    0.07
     infancy
    0.07
    нения
    0.07
     Whoever
    0.06
    Act Density 0.016%

    No Known Activations