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

    Neuronpedia

    INDEX
    Explanations

    sens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     paving
    -0.08
    identify
    -0.08
    .cod
    -0.07
     pave
    -0.07
    nid
    -0.07
    ]|
    -0.07
    ctime
    -0.07
    滋
    -0.07
     Cod
    -0.07
    Cod
    -0.07
    POSITIVE LOGITS
     connection
    0.08
     CONNECTION
    0.08
     ub
    0.08
     toothbrush
    0.07
    นั้น
    0.07
     پور
    0.07
     socks
    0.07
     Ub
    0.07
     vs
    0.07
     Connection
    0.07
    Act Density 0.001%

    No Known Activations