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

    Neuronpedia

    INDEX
    Explanations

    code and file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chewing
    -0.07
    �
    -0.07
     sunk
    -0.07
     pré
    -0.06
     Tavern
    -0.06
     пи
    -0.06
    hů
    -0.06
     diagn
    -0.06
     lavender
    -0.06
     sinks
    -0.06
    POSITIVE LOGITS
    swing
    0.08
     [])
    0.07
    	trace
    0.06
    /example
    0.06
     permission
    0.06
    ../
    0.06
     minions
    0.06
    เวลา
    0.06
    /Foundation
    0.06
    /pkg
    0.06
    Act Density 0.000%

    No Known Activations