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

    Neuronpedia

    INDEX
    Explanations

    references to the number "two" in various contexts

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

    "two"

    np_acts-logits-general · gemini-2.0-flash

    two of something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -1.04
     Jefus
    -1.02
     himſelf
    -0.98
     houſe
    -0.93
     Cæsar
    -0.92
     fubject
    -0.91
     ſche
    -0.91
     ſtate
    -0.91
     myſelf
    -0.91
     Shakspeare
    -0.89
    POSITIVE LOGITS
     two
    0.92
     Two
    0.79
     big
    0.71
     dua
    0.68
    abetes
    0.66
    NameInMap
    0.64
     två
    0.64
     main
    0.64
    Zwei
    0.63
    两
    0.62
    Act Density 0.229%

    No Known Activations