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

    Neuronpedia

    INDEX
    Explanations

    references to academic or research-related entities

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

    Dutch words and abbreviations

    np_acts-logits-general · gemini-2.0-flash

    veranderTiled function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     purpoſe
    -1.33
     ſeveral
    -1.29
     houſe
    -1.28
     Chriftian
    -1.25
     Diſ
    -1.23
     themſelves
    -1.23
     greateſt
    -1.23
     Reſ
    -1.23
     Houſe
    -1.20
     raiſ
    -1.19
    POSITIVE LOGITS
    )]:
    0.65
    "]);
    0.64
    )}>
    0.61
     bek
    0.59
     wen
    0.55
    '}>
    0.54
    "])
    0.54
    )':
    0.54
     op
    0.54
     ken
    0.53
    Act Density 0.027%

    No Known Activations