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

    Neuronpedia

    INDEX
    Explanations

    instances of structural or formatting elements in written documents

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

    shows the results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ''}
    -0.40
    orianCalendar
    -0.39
     Мексичка
    -0.39
    FontOfSize
    -0.38
     stimmen
    -0.36
     removeFrom
    -0.35
    rillation
    -0.34
    뀔
    -0.34
     UIFont
    -0.34
    official
    -0.34
    POSITIVE LOGITS
     disambiguazione
    0.64
    expandindo
    0.56
     snippetHide
    0.54
     يتيمه
    0.54
    rungsseite
    0.53
    
    0.50
    tenti
    0.48
    舺
    0.47
     ujednoznacz
    0.47
     surla
    0.45
    Act Density 0.070%

    No Known Activations