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

    Neuronpedia

    INDEX
    Explanations

    nearness or amount

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    క్స్
    0.66
    вки
    0.66
     optimizer
    0.63
    ónicos
    0.63
    したり
    0.61
    𝑫
    0.61
     diagonalization
    0.59
    hesize
    0.59
    ława
    0.58
    ɵ
    0.58
    POSITIVE LOGITS
     거의
    0.90
     nearly
    0.88
    nearly
    0.77
     almost
    0.76
     more
    0.75
    almost
    0.73
    Nearly
    0.72
     prawie
    0.72
     আরো
    0.70
     Nearly
    0.68
    Act Density 0.006%

    No Known Activations