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

    Neuronpedia

    INDEX
    Explanations

    embark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dop
    -0.08
    꿔
    -0.07
     Laurent
    -0.07
     Hassan
    -0.07
    GRP
    -0.07
    滾
    -0.07
    Outlet
    -0.07
    oren
    -0.07
     '",
    -0.07
     LDL
    -0.07
    POSITIVE LOGITS
    object
    0.08
    кт
    0.08
    .Repositories
    0.07
    �
    0.06
    =function
    0.06
    ypical
    0.06
    можем
    0.06
    command
    0.06
    密切相关
    0.06
    か
    0.06
    Act Density 0.006%

    No Known Activations