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

    Neuronpedia

    INDEX
    Explanations

    instances of information being leaked

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

    leaking information to the wrong hands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.41
     toege
    -0.40
    featureID
    -0.38
     perspective
    -0.34
    archivi
    -0.33
     CCP
    -0.33
     Fil
    -0.32
    Personendaten
    -0.31
    Fil
    -0.31
    DOCTYPE
    -0.31
    POSITIVE LOGITS
     kasarigan
    0.73
    Хьажоргаш
    0.67
    Билгалдахарш
    0.55
     unknownFields
    0.55
    migrationBuilder
    0.55
     ProtoMessage
    0.52
    ViewImports
    0.52
    جغرافيا
    0.52
    BeginContext
    0.50
     للمعارف
    0.48
    Act Density 0.037%

    No Known Activations