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
    (mysql
    -0.06
     обла
    -0.06
    _DEPTH
    -0.06
     Diamonds
    -0.06
     pills
    -0.06
     Rogue
    -0.06
    ่าน
    -0.06
     BUF
    -0.06
    ("%
    -0.06
     gzip
    -0.06
    POSITIVE LOGITS
    生的
    0.07
    眼睛
    0.07
     індив
    0.07
    ينه
    0.06
    ottage
    0.06
     PodsDummy
    0.06
     реє
    0.06
     Ông
    0.06
    χία
    0.06
     Hob
    0.06
    Act Density 0.136%

    No Known Activations