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

    Neuronpedia

    INDEX
    Explanations

    changing generational work dynamics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    пов
    0.46
    mental
    0.45
    ப்புக
    0.44
    тельными
    0.44
    בוד
    0.43
    may
    0.43
    भग
    0.42
     इससे
    0.42
    fet
    0.41
    foaf
    0.41
    POSITIVE LOGITS
     왜
    0.47
     해당
    0.47
    𝙚
    0.46
     autour
    0.45
     docking
    0.45
     મોટી
    0.45
    etails
    0.45
     នៅ
    0.44
     हेल्दी
    0.44
     chew
    0.44
    Act Density 0.002%

    No Known Activations