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

    Neuronpedia

    INDEX
    Explanations

    numerical representations of years or time periods

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

    numbers identifying quantities or ages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     שוליים
    -0.58
    rrggbb
    -0.56
    ########.
    -0.52
     Biôgrafia
    -0.51
     ویکی‌پدیای
    -0.50
     Савезне
    -0.49
     Италијани
    -0.49
     censiti
    -0.49
    UnusedPrivate
    -0.48
     Wikimedijinoj
    -0.47
    POSITIVE LOGITS
     betweenstory
    0.49
    transQ
    0.45
     StatelessWidget
    0.44
     automat
    0.42
     sex
    0.39
     graduate
    0.38
     Jef
    0.38
     abito
    0.37
    teeth
    0.37
     Espa
    0.36
    Act Density 0.015%

    No Known Activations