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

    Neuronpedia

    INDEX
    Explanations

    children's TV shows

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .dataset
    -0.10
     Dataset
    -0.09
    Dataset
    -0.08
    ըն
    -0.08
     Postgre
    -0.08
     beurs
    -0.08
     dataset
    -0.08
     postgres
    -0.08
    postgres
    -0.08
     luks
    -0.08
    POSITIVE LOGITS
     quirky
    0.14
     antics
    0.13
     comedic
    0.12
     whimsical
    0.12
     adventures
    0.12
     goofy
    0.11
     misch
    0.11
     юм
    0.10
    搞
    0.10
     humorous
    0.10
    Act Density 0.066%

    No Known Activations