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

    Neuronpedia

    INDEX
    Explanations

    articles and "be"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    election
    -0.07
    thy
    -0.06
     lis
    -0.06
     вк
    -0.06
    Suddenly
    -0.06
    [random
    -0.06
    нюю
    -0.06
     Suddenly
    -0.06
    iation
    -0.06
    ستان
    -0.06
    POSITIVE LOGITS
     )(
    0.07
    	push
    0.07
     loaded
    0.07
     úrov
    0.06
     caucus
    0.06
    胸
    0.06
     sacked
    0.06
     visiting
    0.06
     Loaded
    0.06
    ManagerInterface
    0.06
    Act Density 0.101%

    No Known Activations