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

    Neuronpedia

    INDEX
    Explanations

    adjacency, neighbors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -fiction
    -0.09
     maling
    -0.08
     slippers
    -0.08
     stationery
    -0.08
    (invoice
    -0.07
     correspondence
    -0.07
    Typeface
    -0.07
    verse
    -0.07
    Og
    -0.07
    -length
    -0.07
    POSITIVE LOGITS
     neighbors
    0.15
    邻
    0.14
     neighbor
    0.14
    neighbors
    0.14
    _neighbors
    0.14
     neighboring
    0.14
    _neighbor
    0.13
    Neighbor
    0.13
     neighbours
    0.13
     Neighbor
    0.13
    Act Density 0.014%

    No Known Activations