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

    Neuronpedia

    INDEX
    Explanations

    narratives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ole
    -0.08
    ！↵↵
    -0.08
     remot
    -0.08
     anytime
    -0.07
     sooner
    -0.07
     રહેશે
    -0.07
    staand
    -0.07
     இருக்கும்
    -0.07
     இருக்க
    -0.07
     clearance
    -0.07
    POSITIVE LOGITS
     बताते
    0.10
     discusses
    0.10
    进行了
    0.09
     argues
    0.09
     предлага
    0.08
    倡
    0.08
     nicely
    0.08
    介绍
    0.08
     બત
    0.08
    介紹
    0.08
    Act Density 0.246%

    No Known Activations