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

    Neuronpedia

    INDEX
    Explanations

    code changes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     момент
    -0.07
    steel
    -0.06
    _regeneration
    -0.06
     маши
    -0.06
    婷
    -0.06
     agent
    -0.06
    аем
    -0.06
    CHAPTER
    -0.06
    EG
    -0.06
    -existent
    -0.06
    POSITIVE LOGITS
    (False
    0.07
    лом
    0.07
    ђ
    0.07
     克
    0.06
     javascript
    0.06
    (relative
    0.06
     νο
    0.06
    _operations
    0.06
     stools
    0.06
     zig
    0.06
    Act Density 0.014%

    No Known Activations