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

    Neuronpedia

    INDEX
    Explanations

    character names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aft
    -0.07
    card
    -0.07
    (goal
    -0.06
     approve
    -0.06
     Editors
    -0.06
    ecal
    -0.06
    orů
    -0.06
    (array
    -0.06
    (trace
    -0.06
    uckle
    -0.06
    POSITIVE LOGITS
     нен
    0.07
    .Sql
    0.07
     Ž
    0.07
    #$
    0.06
     spatial
    0.06
     حضرت
    0.06
    笔
    0.06
    лючается
    0.06
     وز
    0.06
    버지
    0.06
    Act Density 0.033%

    No Known Activations