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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the implementation or commencement of laws and regulations

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

    things going into effect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    qrstuvwxyz
    -0.49
    argout
    -0.44
    findpost
    -0.44
     InputDecoration
    -0.43
    RegressionTest
    -0.41
    inSlope
    -0.41
     seguimiento
    -0.41
     refugi
    -0.40
    AsUp
    -0.40
    atown
    -0.40
    POSITIVE LOGITS
    生效
    0.50
     effect
    0.45
     expired
    0.45
    施行
    0.44
    effect
    0.44
    effective
    0.43
     expire
    0.43
     effective
    0.42
     effetto
    0.42
     vigueur
    0.41
    Act Density 0.199%

    No Known Activations