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

    Neuronpedia

    INDEX
    Explanations

    special characters and certain programming-related keywords or syntax patterns

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

    Vietnamese characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gynnwys
    -0.50
    Identyfik
    -0.47
     snippetHide
    -0.46
    DataBinding
    -0.46
    VYMaps
    -0.46
    httphttps
    -0.46
    Tembelea
    -0.45
     saites
    -0.43
    puted
    -0.42
    Harrison
    -0.41
    POSITIVE LOGITS
    ơ
    2.02
     cơ
    1.47
    Ơ
    1.45
    Ư
    1.28
     Cơ
    1.18
    ư
    1.02
    ươ
    0.90
    ờ
    0.78
     sơ
    0.77
     thơ
    0.70
    Act Density 0.002%

    No Known Activations