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

    Neuronpedia

    INDEX
    Explanations

    achieving beyond prediction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    కుంది
    0.52
    MyShop
    0.50
     Whilst
    0.49
     首先
    0.49
    Entry
    0.47
    Device
    0.47
    StatusCommand
    0.47
    LOTRE
    0.47
    Ft
    0.47
    DbType
    0.47
    POSITIVE LOGITS
     attainable
    0.51
    k
    0.47
     cellules
    0.47
     achievable
    0.45
    delta
    0.45
    wig
    0.43
     to
    0.43
     signifie
    0.43
     tractable
    0.43
     allocations
    0.42
    Act Density 0.001%

    No Known Activations