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

    Neuronpedia

    INDEX
    Explanations

    numeric data or mathematical expressions

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

    numbers and mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite

    mathematical notation and formulas, especially sequences of numbers, variables in parentheses, arithmetic operators, and LaTeX-style expressions.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.84
     Савезне
    -0.75
    :✨
    -0.74
     Numerade
    -0.73
     Wikimedijinoj
    -0.71
     Италијани
    -0.70
    лтамалар
    -0.70
     autorytatywna
    -0.69
    Autoritní
    -0.68
    ंदीखरीदारी
    -0.66
    POSITIVE LOGITS
     NUKAT
    0.34
    ButterKnife
    0.33
    AnchorTagHelper
    0.32
    EndContext
    0.32
    formik
    0.31
    WriteBarrier
    0.30
    (!__
    0.29
    WithIdentifier
    0.29
    Према
    0.28
    meyi
    0.28
    Act Density 18.966%

    No Known Activations