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

    Neuronpedia

    INDEX
    Explanations

    full-fat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     évén
    0.36
    terrorism
    0.35
     비롯
    0.34
     विचारधारा
    0.33
     言っ
    0.33
     terrorism
    0.33
     காரண
    0.32
     ανθρώ
    0.32
     राजनीतिक
    0.31
    犯罪
    0.31
    POSITIVE LOGITS
     Magnesium
    0.41
     magnesium
    0.40
     lavender
    0.40
     Lidl
    0.40
     walnut
    0.37
     Tiki
    0.37
     wooden
    0.37
     DCM
    0.36
     Blu
    0.36
     rosemary
    0.36
    Act Density 0.105%

    No Known Activations