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

    Neuronpedia

    INDEX
    Explanations

    6

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nuis
    -0.08
     AppModule
    -0.07
    .Cho
    -0.07
    人民银行
    -0.07
    uide
    -0.07
    这就是
    -0.07
    _TASK
    -0.07
     chores
    -0.06
    .qml
    -0.06
    .leadingAnchor
    -0.06
    POSITIVE LOGITS
    Rates
    0.07
    עו
    0.07
    ...↵↵↵↵
    0.07
     brutal
    0.07
     DateFormat
    0.07
     sequence
    0.07
    Fuck
    0.07
     sailors
    0.07
    벱
    0.07
     오�
    0.06
    Act Density 0.005%

    No Known Activations