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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence structure

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

    Formatting related to math or dates

    np_acts-logits-general · gemini-2.0-flash

    mathematical and code-like structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rhestr
    -0.75
     الرخصة
    -0.69
     Wikimedijinoj
    -0.66
    parsedMessage
    -0.65
     createSlice
    -0.63
     AppModule
    -0.63
    dział
    -0.61
    قایناق‌لار
    -0.60
    weiterlesen
    -0.59
    Diweddarwch
    -0.59
    POSITIVE LOGITS
     Date
    0.62
    Date
    0.58
     
    0.53
     which
    0.47
    CodedInputStream
    0.46
    <eos>
    0.42
     All
    0.41
     Buy
    0.41
    waypoints
    0.41
    which
    0.40
    Act Density 0.049%

    No Known Activations