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

    Neuronpedia

    INDEX
    Explanations

    NLP models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    温泉
    -0.07
    奢华
    -0.07
    FRAME
    -0.07
    黄昏
    -0.07
    _account
    -0.07
    Definition
    -0.07
    _pages
    -0.07
     stamina
    -0.06
    -learning
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    为代表
    0.08
    CW
    0.07
     prefers
    0.07
    悰
    0.07
    开启了
    0.07
    	Rect
    0.07
     presidency
    0.07
    首位
    0.07
    olut
    0.07
    .vars
    0.06
    Act Density 0.073%

    No Known Activations