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

    Neuronpedia

    INDEX
    Explanations

    thank

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NSIndexPath
    -0.06
    ULK
    -0.06
     initi
    -0.06
     Ik
    -0.06
    ，那
    -0.06
     Bain
    -0.06
    -short
    -0.06
    upakan
    -0.06
    Bài
    -0.06
    ype
    -0.06
    POSITIVE LOGITS
     σημαν
    0.07
     thank
    0.07
    ="#">
    0.06
     north
    0.06
    .om
    0.06
    arc
    0.06
     Populate
    0.06
    ån
    0.05
     tele
    0.05
     cast
    0.05
    Act Density 0.010%

    No Known Activations