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

    Neuronpedia

    INDEX
    Explanations

    contrasts, timeframes, or counterpoints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     괜찮
    0.88
    不够
    0.81
     ayarl
    0.78
     चांगली
    0.77
     wieder
    0.75
    tilde
    0.75
     يا
    0.73
    widetilde
    0.73
    常用的
    0.72
    स
    0.71
    POSITIVE LOGITS
     Despite
    1.60
     despite
    1.38
    Despite
    1.35
     controversies
    1.26
    despite
    1.25
     Generations
    1.17
     generations
    1.08
     Ironically
    1.08
     centuries
    1.08
     decades
    1.07
    Act Density 0.299%

    No Known Activations