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

    Neuronpedia

    INDEX
    Explanations

    periods at the end of sentences

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

    Follows a number and a period

    np_acts-logits-general · gemini-2.0-flash

    numbers and math operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :"-"`
    -0.50
     Ben
    -0.48
    bitol
    -0.47
     ...
    -0.46
     http
    -0.46
    ēm
    -0.46
     Pal
    -0.45
    herokuapp
    -0.44
     Joel
    -0.44
    ...
    -0.44
    POSITIVE LOGITS
    :✨
    0.88
    NameInMap
    0.83
    Hochspringen
    0.79
     يتيمه
    0.78
     ujednoznacz
    0.78
    ########.
    0.67
    AlterField
    0.67
     autorytatywna
    0.66
     inflater
    0.65
    makeConstraints
    0.62
    Act Density 0.006%

    No Known Activations