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

    Neuronpedia

    INDEX
    Explanations

    references to credentials or security-related terms

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

    credentials and acknowledgements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Linder
    -0.54
     Maurer
    -0.51
    <bos>
    -0.48
     McDonald
    -0.47
     Macdonald
    -0.47
     Schultz
    -0.46
     Ziegler
    -0.46
     McNeil
    -0.45
     Pitman
    -0.45
    DVD
    -0.45
    POSITIVE LOGITS
     Cred
    0.83
    cred
    0.79
     cred
    0.77
    alog
    0.75
    Cred
    0.75
     CRED
    0.71
     Sequoia
    0.59
    ferrous
    0.59
     CQ
    0.59
    Viitteet
    0.59
    Act Density 0.019%

    No Known Activations