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

    Neuronpedia

    INDEX
    Explanations

    domain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.09
     sid
    -0.08
     scholarly
    -0.08
     oft
    -0.08
    (RE
    -0.08
     DIN
    -0.08
     Rudy
    -0.08
     Rog
    -0.07
     Pedi
    -0.07
     reputed
    -0.07
    POSITIVE LOGITS
     architecture
    0.09
     Architecture
    0.08
     বিভাগ
    0.07
     Maze
    0.07
     반
    0.07
    Architecture
    0.07
    architecture
    0.07
    isebenzi
    0.07
     desenc
    0.07
    pass
    0.07
    Act Density 0.001%

    No Known Activations