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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    copyright
    -0.06
    _bonus
    -0.06
    cluir
    -0.06
    enade
    -0.06
     Invent
    -0.06
     gems
    -0.06
     crappy
    -0.06
    ater
    -0.06
     етап
    -0.06
     scram
    -0.06
    POSITIVE LOGITS
       ↵
    0.07
    ”↵↵
    0.07
    .TimeUnit
    0.07
           ↵
    0.07
     ↵↵↵↵
    0.06
         ↵
    0.06
    ​↵↵
    0.06
     WebElement
    0.06
     Aaron
    0.06
    	Player
    0.06
    Act Density 0.005%

    No Known Activations