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

    Neuronpedia

    INDEX
    Explanations

    occurrences of symbols, punctuation, and special characters

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

    French and Spanish texts, code helpers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rac
    -0.35
     Withers
    -0.35
     business
    -0.35
    곧
    -0.34
     Schaefer
    -0.34
     gubern
    -0.33
     Simms
    -0.33
     Race
    -0.33
     pied
    -0.33
     Airport
    -0.33
    POSITIVE LOGITS
     surla
    1.06
    WriteTagHelper
    0.91
    ьаж
    0.85
     disambiguazione
    0.82
     للمعارف
    0.82
    ########.
    0.77
     يتيمه
    0.76
     للاسماء
    0.73
    AddTagHelper
    0.71
    GTCX
    0.71
    Act Density 0.008%

    No Known Activations