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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dataSource
    -0.06
     Orbit
    -0.06
     Kaiser
    -0.06
    	App
    -0.06
    tuğ
    -0.06
     ')';↵
    -0.06
    =add
    -0.06
    cover
    -0.06
     EMAIL
    -0.06
    ASE
    -0.06
    POSITIVE LOGITS
    чів
    0.06
    /classes
    0.06
    :
    0.06
    olut
    0.06
    .*;
↵
↵
    0.06
     ilk
    0.06
    !?
    0.06
     typealias
    0.06
    石
    0.06
     연
    0.06
    Act Density 0.022%

    No Known Activations