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

    Neuronpedia

    INDEX
    Explanations

    references to academic honors and notable locations related to higher education or research

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

    universities, cities, and historical figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.75
     ſch
    -0.64
     Monfieur
    -0.63
     myſelf
    -0.62
     ſte
    -0.61
     raiſ
    -0.61
     Majefty
    -0.60
     quæ
    -0.57
     ſta
    -0.57
     greateſt
    -0.57
    POSITIVE LOGITS
     Rotterdam
    1.16
    terdam
    0.93
     Leiden
    0.88
     laude
    0.79
    toContain
    0.67
     Delft
    0.64
     Utrecht
    0.64
    BagLayout
    0.54
     Dutch
    0.52
     CNRS
    0.47
    Act Density 0.004%

    No Known Activations