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

    Neuronpedia

    INDEX
    Explanations

    referencing something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ಮಾಡ
    -0.08
    384
    -0.07
    ajin
    -0.07
    .mar
    -0.07
    פ
    -0.07
    .ft
    -0.07
    arel
    -0.07
     transforms
    -0.07
    Motor
    -0.07
     spro
    -0.07
    POSITIVE LOGITS
     refers
    0.14
     referring
    0.13
     refiere
    0.11
     preceding
    0.11
     referido
    0.11
     относится
    0.10
     referencing
    0.10
     rifer
    0.10
    oree
    0.09
     wcześ
    0.09
    Act Density 0.055%

    No Known Activations