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

    Neuronpedia

    INDEX
    Explanations

    Lists in code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Brink
    -0.08
     demeanor
    -0.07
    測
    -0.07
     अख
    -0.07
     Nish
    -0.07
     Ren
    -0.07
    metik
    -0.07
    -0.07
     reneg
    -0.07
     �
    -0.07
    POSITIVE LOGITS
     [[]
    0.13
     defaultdict
    0.11
     adjacency
    0.10
     Listings
    0.10
     listas
    0.09
     lists
    0.09
     listings
    0.09
    _lists
    0.09
     Lists
    0.09
     biodivers
    0.09
    Act Density 0.005%
    No Known Activations