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

    Neuronpedia

    INDEX
    Explanations

    developed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    todos
    -0.07
    极力
    -0.07
    PropTypes
    -0.07
    埔
    -0.07
    emens
    -0.07
    boxed
    -0.07
     rahats
    -0.07
    万分
    -0.07
    杙
    -0.07
    顷
    -0.07
    POSITIVE LOGITS
    _rep
    0.07
     Payload
    0.07
    _TM
    0.07
     possible
    0.07
     equivalent
    0.06
    ⚟
    0.06
    物质
    0.06
     Is
    0.06
     ")↵↵
    0.06
     constants
    0.06
    Act Density 0.001%

    No Known Activations