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

    Neuronpedia

    INDEX
    Explanations

    code output/lists/responses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ;m
    -0.07
     Tavern
    -0.07
    PDO
    -0.07
    522
    -0.06
    �
    -0.06
     McCartney
    -0.06
     embodiment
    -0.06
     Ming
    -0.06
    ;d
    -0.06
    ;t
    -0.06
    POSITIVE LOGITS
     rewrite
    0.07
     executor
    0.07
    .Perform
    0.06
    ประว
    0.06
    urtle
    0.06
     �
    0.06
    ／/
    0.06
     thoroughly
    0.06
    .getNum
    0.06
     Brilliant
    0.06
    Act Density 0.003%

    No Known Activations