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

    Neuronpedia

    INDEX
    Explanations

    World

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    牧
    -0.08
     protože
    -0.06
    ITTLE
    -0.06
     grease
    -0.06
     VIEW
    -0.06
     ">
    -0.06
    ————
    -0.06
     πρώτη
    -0.05
     officers
    -0.05
     Drive
    -0.05
    POSITIVE LOGITS
     Posting
    0.08
    	select
    0.07
    :Boolean
    0.07
    ,､
    0.06
     модели
    0.06
    éré
    0.06
    lucent
    0.06
    Association
    0.06
    	inst
    0.06
    егра
    0.06
    Act Density 0.010%

    No Known Activations