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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and periods in text

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

    legal citations and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Royaume
    -0.41
     تضيفلها
    -0.41
    qtype
    -0.37
    nhung
    -0.36
    期
    -0.35
     typelib
    -0.35
    untamiento
    -0.35
    styleable
    -0.34
    配
    -0.33
    Redaktion
    -0.33
    POSITIVE LOGITS
    ſelf
    0.69
    PreferredItem
    0.68
     initComponents
    0.62
     houſe
    0.59
    PyExc
    0.57
    ſelves
    0.57
     canadensis
    0.56
     itſelf
    0.56
    parsedMessage
    0.55
     nonUne
    0.54
    Act Density 0.001%

    No Known Activations