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

    Neuronpedia

    INDEX
    Explanations

    defining terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ેડ
    -0.08
     resil
    -0.08
    プ
    -0.07
     periodic
    -0.07
    _ENABLED
    -0.07
    Enabled
    -0.07
     result
    -0.07
     resumed
    -0.07
    ITUDE
    -0.07
    Periodic
    -0.07
    POSITIVE LOGITS
     definitions
    0.16
     Definitions
    0.15
    Definitions
    0.14
     정의
    0.13
    definitions
    0.13
    定义
    0.13
     defs
    0.13
    initions
    0.13
     glossary
    0.12
     تعریف
    0.12
    Act Density 0.074%

    No Known Activations