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

    Neuronpedia

    INDEX
    Explanations

    */

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    των
    -0.06
     lifestyle
    -0.06
    Profit
    -0.06
    fortune
    -0.06
    680
    -0.06
    мон
    -0.06
     controversy
    -0.06
    (call
    -0.06
    director
    -0.06
    ’t
    -0.06
    POSITIVE LOGITS
    ensely
    0.07
     Marks
    0.07
     Swagger
    0.07
     Portions
    0.07
     pokus
    0.06
     Vec
    0.06
     ```
    0.06
     Advance
    0.06
    ``
    0.06
     fmap
    0.06
    Act Density 0.005%

    No Known Activations