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
     solves
    -0.07
     Help
    -0.07
     Elves
    -0.07
     sworn
    -0.07
     reson
    -0.07
    /color
    -0.07
     continuum
    -0.07
    thumbs
    -0.07
    出现
    -0.06
    社會
    -0.06
    POSITIVE LOGITS
     Dustin
    0.07
     ardından
    0.07
    (ab
    0.06
    ('');↵
    0.06
    \Migration
    0.06
    攻撃
    0.06
     โรง
    0.06
    -secondary
    0.06
    duk
    0.06
    	DB
    0.06
    Act Density 0.013%

    No Known Activations