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

    Neuronpedia

    INDEX
    Explanations

    references to concepts of transcendence or going beyond normal limits

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

    "beyond"

    np_acts-logits-general · gemini-2.0-flash

    exceeding limits or scope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     omge
    -0.48
    beforeEach
    -0.42
    InstanceState
    -0.42
    colhead
    -0.41
     nocturn
    -0.40
    яза
    -0.40
     πολ
    -0.40
    components
    -0.39
     jeito
    -0.39
     SP
    -0.38
    POSITIVE LOGITS
     hinaus
    1.11
     beyond
    0.99
    beyond
    0.95
     boundaries
    0.93
     Beyond
    0.92
    Beyond
    0.91
     BEYOND
    0.90
    YOND
    0.90
     bounds
    0.88
    NameInMap
    0.83
    Act Density 0.188%

    No Known Activations