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

    Neuronpedia

    INDEX
    Explanations

    why it's happening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Или
    0.47
     Hyundai
    0.45
     алыңыз
    0.45
    чные
    0.45
     गैर
    0.45
     Featuring
    0.45
    FERENCE
    0.44
     MAX
    0.43
    MAX
    0.43
     прочита
    0.42
    POSITIVE LOGITS
     predicates
    0.46
     are
    0.45
     tuples
    0.45
     tuple
    0.44
     constituting
    0.43
     stakeholder
    0.42
     object
    0.42
     disconnection
    0.41
     partitions
    0.41
     targets
    0.40
    Act Density 0.000%

    No Known Activations