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

    Neuronpedia

    INDEX
    Explanations

    scientific abstracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Boolean
    -0.07
    aría
    -0.07
     Dire
    -0.06
     seminal
    -0.06
    oub
    -0.06
     Screens
    -0.06
     algum
    -0.06
    细
    -0.06
     hatten
    -0.06
     promotes
    -0.06
    POSITIVE LOGITS
    DbContext
    0.07
    	values
    0.06
     zam
    0.06
    โย
    0.06
    [args
    0.06
    .VALUE
    0.06
    tableView
    0.06
     wij
    0.06
     tùy
    0.06
    highlight
    0.06
    Act Density 0.001%

    No Known Activations