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

    Neuronpedia

    INDEX
    Explanations

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     তাহাদের
    0.50
    धित
    0.49
     leptons
    0.48
    atthanam
    0.48
     ayatan
    0.46
     coals
    0.45
    বর্ধমান
    0.45
     dominions
    0.45
     /
    0.44
     цар
    0.44
    POSITIVE LOGITS
    3
    0.70
    5
    0.70
     the
    0.64
    还有
    0.63
     اینکه
    0.63
     nói
    0.62
    4
    0.62
    此外
    0.62
     diğer
    0.62
     ayrıca
    0.62
    Act Density 0.033%

    No Known Activations