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

    Neuronpedia

    INDEX
    Explanations

    open

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bonus
    -0.06
     dai
    -0.06
    τερ
    -0.06
    อาร
    -0.06
    님이
    -0.06
     vốn
    -0.06
     Олександ
    -0.06
    워
    -0.06
    wcsstore
    -0.06
    -ф
    -0.06
    POSITIVE LOGITS
     open
    0.17
    -open
    0.11
     Open
    0.10
    	open
    0.08
    Open
    0.08
    open
    0.08
     closed
    0.08
     OPEN
    0.07
     unlock
    0.07
     unlocks
    0.07
    Act Density 0.012%

    No Known Activations