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

    Neuronpedia

    INDEX
    Explanations

    quantifiers and descriptive phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ngunit
    0.28
     whose
    0.26
     nidd
    0.24
     그리고
    0.24
     (*
    0.24
    》，
    0.23
     இந்நிலையில்
    0.22
     נישט
    0.22
     maß
    0.22
     但
    0.22
    POSITIVE LOGITS
    人都
    0.29
    多くの
    0.24
    人は
    0.23
     लोग
    0.22
     experts
    0.22
    會有
    0.22
     companies
    0.22
     proponents
    0.22
     многое
    0.21
    很
    0.21
    Act Density 0.334%

    No Known Activations