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

    Neuronpedia

    INDEX
    Explanations

    asset types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     میں
    0.42
    پ
    0.42
    或
    0.42
     بدون
    0.41
    ẫn
    0.41
     عند
    0.39
    ências
    0.39
    in
    0.39
    ife
    0.38
    وک
    0.38
    POSITIVE LOGITS
     вещества
    0.50
     creada
    0.49
     pita
    0.46
    ONTAL
    0.46
    떻
    0.46
     言っ
    0.45
     nutric
    0.45
     옷
    0.45
     диагности
    0.45
     考え
    0.45
    Act Density 0.003%

    No Known Activations