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

    Neuronpedia

    INDEX
    Explanations

    specifically relating to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    altitude
    0.39
    Government
    0.39
    Graz
    0.38
    Governor
    0.36
    Govern
    0.35
    institute
    0.35
    線上
    0.35
    Rein
    0.34
    isDirectory
    0.34
    grade
    0.34
    POSITIVE LOGITS
     WordPress
    0.84
     MNIST
    0.84
     AutoCAD
    0.81
     Wordpress
    0.79
     Ethereum
    0.77
     Beatles
    0.77
     Skyrim
    0.77
     Ubuntu
    0.73
     MySQL
    0.73
     Chardonnay
    0.73
    Act Density 0.027%

    No Known Activations