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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ses
    -0.07
     ′
    -0.06
     форме
    -0.06
     Web
    -0.06
    ellow
    -0.06
     určit
    -0.06
     roundup
    -0.06
    -min
    -0.06
    qtt
    -0.06
    ará
    -0.06
    POSITIVE LOGITS
     हट
    0.07
     Interesting
    0.07
     embarked
    0.06
     FOOD
    0.06
     정치
    0.06
     Impro
    0.06
    ,{
    0.06
    _artist
    0.06
    “This
    0.06
     vandal
    0.06
    Act Density 0.001%

    No Known Activations