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

    Neuronpedia

    INDEX
    Explanations

    references to research papers or external sources, often indicated by bracketed numbers

    oai_token-act-pair · gemini-2.0-flash

    technical document elements or references

    np_token-act-pair-logits · gpt-4o-mini

    citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ninth
    -0.76
     Ninth
    -0.76
     ninety
    -0.75
    9
    -0.67
     Ninety
    -0.65
    ９
    -0.64
    第九
    -0.63
     nine
    -0.62
     September
    -0.62
     Nine
    -0.61
    POSITIVE LOGITS
    SequentialGroup
    0.59
    ugc
    0.59
     Autorizaciones
    0.58
    BufferException
    0.57
    usercontent
    0.54
    iStock
    0.48
    Establishing
    0.48
     Establishing
    0.47
    DoubleQuotes
    0.46
    scalatest
    0.46
    Act Density 2.827%

    No Known Activations