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

    Neuronpedia

    INDEX
    Explanations

    references to historical events and periods

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

    years and centuries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.83
    ſicht
    -0.79
     EconPapers
    -0.79
     queſta
    -0.78
    ロウィン
    -0.77
    ſchaft
    -0.76
    <unused79>
    -0.75
    <unused41>
    -0.75
    <unused8>
    -0.75
    <pad>
    -0.75
    POSITIVE LOGITS
     энциклопедия
    0.33
     Jahres
    0.33
     year
    0.28
     conoz
    0.26
     repente
    0.26
     kés
    0.25
     année
    0.25
     años
    0.25
     years
    0.25
     fréqu
    0.25
    Act Density 0.066%

    No Known Activations