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

    Neuronpedia

    INDEX
    Explanations

    specific symbols, punctuation, and formatting styles within text

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

    apache commons math fraction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uitz
    -0.49
    arsis
    -0.45
    ungal
    -0.45
    uxi
    -0.44
    habi
    -0.44
    ssy
    -0.43
    ksha
    -0.43
    ung
    -0.43
    crum
    -0.43
    ungu
    -0.43
    POSITIVE LOGITS
    SBATCH
    0.60
     bezeichneter
    0.59
    OGND
    0.59
    expandindo
    0.59
    0.59
    GEBURTSDATUM
    0.57
    istoitu
    0.57
     ExecuteAsync
    0.57
     CascadeType
    0.54
     AssemblyCompany
    0.52
    Act Density 0.039%

    No Known Activations