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

    Neuronpedia

    INDEX
    Explanations

    references to secrecy and secret organizations

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

    "secret" or its variations

    np_acts-logits-general · gemini-2.0-flash

    secret concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.75
    DeleteBehavior
    -0.73
    verwijspagina
    -0.72
     مرئيه
    -0.66
    fillType
    -0.65
    SerializedSize
    -0.65
    uinal
    -0.63
    MigrationBuilder
    -0.62
    NameInMap
    -0.61
    іга
    -0.60
    POSITIVE LOGITS
     Sec
    0.82
     SECRET
    0.74
     SEC
    0.70
     Secret
    0.67
    Sec
    0.67
     sec
    0.64
    SECUR
    0.63
    Secret
    0.60
     Secre
    0.60
    espace
    0.58
    Act Density 0.161%

    No Known Activations