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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating relationships or specifications of ideas

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

    temporal periods and ages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    styleType
    -0.79
    parsedMessage
    -0.72
     PeEnEo
    -0.66
     kaynağından
    -0.62
    Aholisi
    -0.62
    Datuak
    -0.62
     GenerationType
    -0.60
    httphttps
    -0.59
     propOrder
    -0.58
    __*/
    -0.57
    POSITIVE LOGITS
     época
    0.56
     geçmiş
    0.54
     década
    0.54
     épocas
    0.54
     années
    0.51
     tahun
    0.50
     years
    0.49
     perioden
    0.47
     vuo
    0.47
     dahulu
    0.44
    Act Density 0.034%

    No Known Activations