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

    Neuronpedia

    INDEX
    Explanations

    mathematical questions and requests for prime factorization

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

    Followed by a list, explaining, or discussing

    np_acts-logits-general · gemini-2.0-flash

    prime factors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.70
     estekak
    -0.68
     indisponible
    -0.66
    )";
    -0.66
     nemlig
    -0.64
     Theſe
    -0.62
    righted
    -0.59
    awtextra
    -0.59
    IntoConstraints
    -0.59
    ghest
    -0.58
    POSITIVE LOGITS
     Explain
    0.68
     your
    0.68
    Explain
    0.64
     yourself
    0.58
    说说
    0.57
     explain
    0.56
     Discuss
    0.56
    MemoryWarning
    0.56
    your
    0.56
     Describe
    0.56
    Act Density 0.282%

    No Known Activations