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

    Neuronpedia

    INDEX
    Explanations

    pay

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nursing
    -0.08
     nutrients
    -0.08
     benchmark
    -0.08
     nutrient
    -0.08
     nghiên
    -0.08
     parenting
    -0.08
     pilot
    -0.08
     במד
    -0.07
     nurturing
    -0.07
     prayer
    -0.07
    POSITIVE LOGITS
     mord
    0.09
     Pourquoi
    0.09
     onmidd
    0.08
     सीधे
    0.08
     kepada
    0.08
    urem
    0.08
    libs
    0.08
     langsung
    0.08
     Risiko
    0.08
     Specifies
    0.08
    Act Density 0.009%

    No Known Activations