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

    Neuronpedia

    INDEX
    Explanations

    at the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     an
    0.84
     rampant
    0.75
     incessant
    0.74
    abhave
    0.73
     ehemaligen
    0.72
     hyvä
    0.70
     suspected
    0.68
     possibilidade
    0.68
    0.68
    abhavena
    0.68
    POSITIVE LOGITS
    수록
    0.69
     menghasilkan
    0.67
     leisten
    0.61
     aantal
    0.60
     feats
    0.60
    餐饮
    0.59
    ැනි
    0.59
     menawarkan
    0.59
     restaurants
    0.58
     drain
    0.58
    Act Density 0.302%

    No Known Activations