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

    Neuronpedia

    INDEX
    Explanations

    opinion pieces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clockwise
    -0.07
    hoot
    -0.07
     yolu
    -0.06
    	inst
    -0.06
    ↵
    -0.06
    ा)
    -0.06
    rounded
    -0.06
     strr
    -0.06
    und
    -0.06
    word
    -0.06
    POSITIVE LOGITS
    持续
    0.07
    _HELP
    0.06
    	None
    0.06
    omba
    0.06
    Registration
    0.06
     favourites
    0.06
    -lnd
    0.06
     closets
    0.06
    	Default
    0.06
     Displays
    0.05
    Act Density 0.033%

    No Known Activations