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

    Neuronpedia

    INDEX
    Explanations

    code structure and backend modules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Introductory
    0.46
     Beginner
    0.41
     ввода
    0.40
     introductory
    0.40
    iftoire
    0.38
     ввод
    0.38
    eleron
    0.38
     Introduction
    0.37
     beginner
    0.36
    resión
    0.35
    POSITIVE LOGITS
    StringUtils
    0.47
     george
    0.45
    qu
    0.42
     firebase
    0.42
     mario
    0.42
    auth
    0.42
    firebase
    0.41
    lz
    0.40
    generate
    0.40
    Cutting
    0.40
    Act Density 0.003%

    No Known Activations