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

    Neuronpedia

    INDEX
    Explanations

    adding ingredients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vattum
    0.37
     hänen
    0.32
     sărb
    0.32
     utilisent
    0.32
    മുണ്ട്
    0.31
     pelanggan
    0.31
    myapplication
    0.31
    acariy
    0.31
     queso
    0.30
     مشتری
    0.30
    POSITIVE LOGITS
    [
    0.32
    ICO
    0.32
    EXT
    0.30
    PE
    0.29
    TR
    0.29
    Three
    0.29
    PL
    0.29
    TO
    0.28
    ARE
    0.28
    A
    0.28
    Act Density 0.162%

    No Known Activations