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

    Neuronpedia

    INDEX
    Explanations

    key terms related to law, politics, and sociology

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

    `super` followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enim
    -0.37
    [])
    -0.36
    cplusplus
    -0.35
     helpful
    -0.34
     Iw
    -0.33
    원
    -0.32
     SR
    -0.32
    Help
    -0.32
    帮
    -0.31
     represents
    -0.31
    POSITIVE LOGITS
    RenderAtEndOf
    0.70
     kasarigan
    0.65
    IUrlHelper
    0.64
    featureID
    0.58
    RegressionTest
    0.56
    zzang
    0.55
    EndProject
    0.55
    TypedDataSet
    0.54
    abetes
    0.53
    verwijspagina
    0.53
    Act Density 0.133%

    No Known Activations