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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting related to math or programming expressions

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

    list item markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.66
     dataList
    -0.57
     roleId
    -0.55
     (_,
    -0.55
     pageNumber
    -0.54
     userSchema
    -0.52
     endblock
    -0.52
    softc
    -0.52
     setState
    -0.52
     ſind
    -0.52
    POSITIVE LOGITS
    úgó
    0.49
    ømme
    0.46
     nyky
    0.46
     parezca
    0.45
     Riesen
    0.45
     cuar
    0.45
     pudieran
    0.44
     כשה
    0.44
     quieras
    0.44
    ihnachts
    0.44
    Act Density 0.318%

    No Known Activations