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

    Neuronpedia

    INDEX
    Explanations

    graph theory/geometry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Length
    -0.09
    	length
    -0.09
    rosion
    -0.08
     الخاصة
    -0.08
     lengths
    -0.07
    titor
    -0.07
    ritic
    -0.07
     unica
    -0.07
     الخاص
    -0.07
    用途
    -0.07
    POSITIVE LOGITS
     neighbor
    0.11
    との
    0.10
     nearby
    0.10
    _neighbor
    0.10
     neighboring
    0.10
    neighbor
    0.10
    邻
    0.09
    Nearby
    0.09
     vecino
    0.09
    Neighbor
    0.09
    Act Density 0.070%

    No Known Activations