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

    Neuronpedia

    INDEX
    Explanations

    game rules/mechanics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chấm
    -0.07
     urč
    -0.07
     Nickel
    -0.06
    Đây
    -0.06
    郡
    -0.06
     ----------------
    -0.06
    城市
    -0.06
    .matrix
    -0.06
     пев
    -0.06
    都是
    -0.06
    POSITIVE LOGITS
    ("<?
    0.08
    (project
    0.06
    depends
    0.06
    boy
    0.06
    Dealer
    0.06
     bull
    0.06
    mandatory
    0.06
     l
    0.06
     Goals
    0.06
    chandle
    0.06
    Act Density 0.013%

    No Known Activations