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

    Neuronpedia

    INDEX
    Explanations

    DLSS and Tensor Processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ប
    0.47
     materialistic
    0.45
    ulpt
    0.45
     protons
    0.45
     diagonalizable
    0.45
    дія
    0.43
    тели
    0.43
    voj
    0.43
    सन्
    0.43
    ей
    0.42
    POSITIVE LOGITS
     Preserve
    0.54
     Protect
    0.52
     Overse
    0.50
     Prevent
    0.49
     aggi
    0.46
     Trust
    0.46
     Watering
    0.46
     WeChat
    0.45
     Neighborhood
    0.45
     Critic
    0.44
    Act Density 0.007%

    No Known Activations