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

    Neuronpedia

    INDEX
    Explanations

    terms related to operational and procedural protocols in various contexts

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

    Importance or criticality

    np_acts-logits-general · gemini-2.0-flash

    critical or important concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     éte
    -0.71
    PreferredItem
    -0.70
    migrationBuilder
    -0.61
    homonymie
    -0.57
    躇
    -0.57
     excès
    -0.57
     gefallen
    -0.57
    paravant
    -0.56
     faite
    -0.55
     offerts
    -0.54
    POSITIVE LOGITS
     important
    2.17
     crucial
    1.97
     critical
    1.96
    important
    1.88
     vital
    1.84
     Important
    1.79
     essential
    1.70
    重要
    1.65
    Important
    1.62
    critical
    1.59
    Act Density 0.660%

    No Known Activations