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

    Neuronpedia

    INDEX
    Explanations

    spheres and circles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     burgl
    -0.09
     statutes
    -0.08
    Furniture
    -0.08
     cyclists
    -0.08
    (IR
    -0.08
    Execute
    -0.08
     periodontal
    -0.07
    弄
    -0.07
    Contracts
    -0.07
     prosecuted
    -0.07
    POSITIVE LOGITS
     sphere
    0.09
     Sphere
    0.09
     reminiscent
    0.08
     esfera
    0.08
     Luna
    0.08
     Soda
    0.08
     spheres
    0.08
     slices
    0.08
     creme
    0.08
    ĵ
    0.08
    Act Density 0.017%

    No Known Activations