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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or symbols related to formal definitions and concepts

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

    LaTeX mathematical symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zkopf
    -0.53
    Билгалдахарш
    -0.44
     risult
    -0.40
     Deal
    -0.39
    BackStack
    -0.38
     Transvaal
    -0.38
     Tsche
    -0.38
     getProperty
    -0.38
     rẻ
    -0.37
    ponses
    -0.36
    POSITIVE LOGITS
     Serena
    1.80
    Serena
    1.67
     serena
    1.33
     seren
    0.99
     Seren
    0.94
     Serenity
    0.74
    Serenity
    0.68
     serene
    0.66
    eren
    0.65
     Celeste
    0.63
    Act Density 0.018%

    No Known Activations