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

    Neuronpedia

    INDEX
    Explanations

    numerical references and related data points in a document

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

    numbers and slashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enciaga
    -0.32
     fabricante
    -0.26
     Friedens
    -0.25
     fabricant
    -0.25
    向
    -0.25
    mphony
    -0.24
     encaps
    -0.24
     Reifen
    -0.24
     Griechen
    -0.23
     Bünd
    -0.23
    POSITIVE LOGITS
     للاسماء
    0.82
    UnusedPrivate
    0.68
    Tembelea
    0.67
    ientras
    0.66
     الرياضيه
    0.65
     $_"
    0.63
    ьаж
    0.62
    <unused43>
    0.62
    <unused14>
    0.62
    <unused28>
    0.62
    Act Density 0.187%

    No Known Activations