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

    Neuronpedia

    INDEX
    Explanations

    engineering descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ffm
    -0.07
    Topology
    -0.07
     Blaze
    -0.07
     아버지
    -0.06
     antim
    -0.06
    _Register
    -0.06
    .Stretch
    -0.06
    wart
    -0.06
     Iranian
    -0.06
     findViewById
    -0.06
    POSITIVE LOGITS
    عکس
    0.07
    fos
    0.06
     thoroughly
    0.06
     München
    0.06
    uly
    0.06
    formedURLException
    0.06
    译
    0.06
    ник
    0.06
     рас
    0.06
     italic
    0.06
    Act Density 0.077%

    No Known Activations