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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    📪
    -0.08
     lost
    -0.08
    	dis
    -0.07
    _reserved
    -0.07
    _PUSH
    -0.07
    纫
    -0.07
     Opening
    -0.07
    隐身
    -0.07
     opening
    -0.07
    鲁迅
    -0.07
    POSITIVE LOGITS
     independents
    0.07
    IM
    0.07
     AT
    0.07
    有多大
    0.07
     Virginia
    0.06
    いで
    0.06
     />)↵
    0.06
     Formula
    0.06
    abal
    0.06
     GAME
    0.06
    Act Density 0.001%

    No Known Activations