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

    Neuronpedia

    INDEX
    Explanations

    de

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    empl
    -0.07
     bundled
    -0.07
    ня
    -0.06
     �
    -0.06
     InkWell
    -0.06
    root
    -0.06
     Penis
    -0.06
     Audrey
    -0.06
    (exec
    -0.06
     atrib
    -0.06
    POSITIVE LOGITS
     comparisons
    0.06
     Mull
    0.06
    .toUpperCase
    0.06
     Commands
    0.06
    机
    0.05
     Retrieved
    0.05
    ('|
    0.05
     Wy
    0.05
    曼
    0.05
    +-+-
    0.05
    Act Density 0.005%

    No Known Activations