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

    Neuronpedia

    INDEX
    Explanations

    food

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    讨厌
    -0.07
    杜绝
    -0.07
    _Filter
    -0.07
    Lady
    -0.07
     thiệt
    -0.07
     gefunden
    -0.07
    _means
    -0.07
     plus
    -0.07
     hey
    -0.07
     Ting
    -0.06
    POSITIVE LOGITS
    خطط
    0.07
    torch
    0.07
    몸
    0.07
     og
    0.06
     Ohio
    0.06
    뎐
    0.06
     argparse
    0.06
    有种
    0.06
     cris
    0.06
     attempting
    0.06
    Act Density 0.048%

    No Known Activations