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

    Neuronpedia

    INDEX
    Explanations

    main

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     facility
    -0.07
    aData
    -0.06
     compos
    -0.06
     Estimates
    -0.06
    ﻴ
    -0.06
     disposit
    -0.06
    _movie
    -0.06
     samples
    -0.06
    .Scheme
    -0.06
     warming
    -0.06
    POSITIVE LOGITS
     κύ
    0.07
    845
    0.07
     main
    0.07
    oğun
    0.06
     inhibited
    0.06
     hlavní
    0.06
     Вид
    0.06
    ”，
    0.06
     (£
    0.06
     userName
    0.06
    Act Density 0.038%

    No Known Activations