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

    Neuronpedia

    INDEX
    Explanations

    comparing and contrasting elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Old
    2.27
     with
    2.15
     Re
    2.06
     slides
    2.03
     Wife
    2.00
     wife
    2.00
     Con
    1.96
     Ne
    1.94
     ・
    1.90
    edia
    1.90
    POSITIVE LOGITS
    {
    1.75
     árabe
    1.44
    CartVO
    1.42
     aliqua
    1.39
     kuiten
    1.36
     makeSound
    1.33
    هایت
    1.33
    {-
    1.32
    rinsic
    1.30
    <unused944>
    1.30
    Act Density 0.069%

    No Known Activations