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

    Neuronpedia

    INDEX
    Explanations

    acronyms and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vdd
    0.38
     gk
    0.36
    yen
    0.35
    gien
    0.35
    owany
    0.34
    gggg
    0.34
    oreille
    0.34
    .•
    0.33
    wadi
    0.32
    tpc
    0.32
    POSITIVE LOGITS
    hereinafter
    0.58
    hereafter
    0.56
    简称
    0.54
     hereafter
    0.53
    commonly
    0.49
     henceforth
    0.48
    以後
    0.47
     hereinafter
    0.47
    referred
    0.46
    AKA
    0.43
    Act Density 0.134%

    No Known Activations