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

    Neuronpedia

    INDEX
    Explanations

    contracts and legal terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ということで
    0.48
    ক্স
    0.47
     inactivació
    0.47
     нагре
    0.47
     увла
    0.47
     ವರ್ಷ
    0.46
     manne
    0.46
    ("~/
    0.46
    ިޔ
    0.46
     bhij
    0.46
    POSITIVE LOGITS
    arios
    0.44
     Contracts
    0.44
    Matthew
    0.41
    Contract
    0.41
     Contract
    0.41
    contract
    0.40
    no
    0.40
    negative
    0.40
    When
    0.39
     When
    0.38
    Act Density 2.924%

    No Known Activations