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

    Neuronpedia

    INDEX
    Explanations

    references to legislative amendments and changes in legal statutes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    changes and additions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الحره
    -0.39
    颠
    -0.37
    WARNINGS
    -0.34
     
    -0.33
     SUT
    -0.32
     Truck
    -0.31
     entière
    -0.31
    -0.31
    DEZ
    -0.31
     Whe
    -0.31
    POSITIVE LOGITS
     recientemente
    0.64
    recently
    0.61
     recentemente
    0.59
     reciente
    0.59
     recente
    0.59
    Recently
    0.55
     recently
    0.54
    InjectAttribute
    0.53
     récemment
    0.52
     récente
    0.52
    Act Density 0.069%

    No Known Activations