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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals and their roles or actions in various contexts

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

    about representation or agents

    np_acts-logits-general · gemini-2.0-flash

    agent or representative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]")]
    -0.45
    MigrationBuilder
    -0.45
    Revenir
    -0.39
    󠁿
    -0.38
     tiveram
    -0.37
    UnitTesting
    -0.37
    Zunanje
    -0.36
     desarrollan
    -0.32
     nationalen
    -0.32
    kebox
    -0.32
    POSITIVE LOGITS
    represent
    0.54
     representative
    0.54
    representative
    0.52
     proxy
    0.51
     representatives
    0.51
    deleg
    0.50
     repres
    0.49
     Representatives
    0.49
    代理
    0.49
    legal
    0.48
    Act Density 0.373%

    No Known Activations