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
    .Build
    -0.06
    ิเว
    -0.06
    Instances
    -0.06
     rnd
    -0.06
    .Factory
    -0.06
    言葉
    -0.06
     içi
    -0.06
    Charles
    -0.06
     salle
    -0.06
    -going
    -0.06
    POSITIVE LOGITS
              ↵
    0.07
    šil
    0.06
    ulpt
    0.06
    UNIT
    0.06
    istrov
    0.06
    lbs
    0.06
    HEST
    0.06
     ",↵
    0.06
    мін
    0.06
    	printk
    0.06
    Act Density 0.003%

    No Known Activations