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

    Neuronpedia

    INDEX
    Explanations

    occurs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     XCTestCase
    -0.07
    Cache
    -0.07
     whereby
    -0.06
    abeth
    -0.06
    �
    -0.06
    	router
    -0.06
     EVAL
    -0.06
    ystatechange
    -0.06
     Shed
    -0.06
    $action
    -0.06
    POSITIVE LOGITS
     allerdings
    0.08
     dés
    0.07
     marches
    0.07
    意
    0.06
    Il
    0.06
     dlou
    0.06
     fri
    0.06
    >i
    0.06
     hors
    0.06
     frowned
    0.06
    Act Density 0.017%

    No Known Activations