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

    Neuronpedia

    INDEX
    Explanations

    bro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MO
    -0.07
    eg
    -0.07
     实
    -0.06
    EG
    -0.06
    \Facades
    -0.06
     reversing
    -0.06
     TX
    -0.06
     HF
    -0.05
    MX
    -0.05
     DW
    -0.05
    POSITIVE LOGITS
     بق
    0.07
    "They
    0.07
     zusammen
    0.07
    _pull
    0.06
     привед
    0.06
     physically
    0.06
    .Padding
    0.06
    _human
    0.06
    )'],↵
    0.06
    (IConfiguration
    0.06
    Act Density 0.141%

    No Known Activations