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

    Neuronpedia

    INDEX
    Explanations

    numerical values, likely indicating categories, ranks, or quantities within a dataset

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

    dates and months

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     boneca
    -0.41
    tagHelperRunner
    -0.41
    💈
    -0.38
     verrez
    -0.37
     miniaturka
    -0.37
     trouvez
    -0.36
    GTCX
    -0.34
     médecin
    -0.34
     torebka
    -0.34
     boneco
    -0.33
    POSITIVE LOGITS
    January
    0.66
    February
    0.66
    June
    0.64
    July
    0.63
    March
    0.62
     August
    0.62
    August
    0.61
    September
    0.60
     February
    0.60
     January
    0.60
    Act Density 0.006%

    No Known Activations