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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     дальше
    -0.08
    דרום
    -0.08
    	gbc
    -0.07
    .WEST
    -0.07
     outra
    -0.07
    凭什么
    -0.07
     selber
    -0.07
    쏘
    -0.07
    ippets
    -0.07
    adelphia
    -0.07
    POSITIVE LOGITS
     зам
    0.08
    ейств
    0.07
     publish
    0.07
    ],$
    0.07
     Activate
    0.07
    (index
    0.07
     reduced
    0.07
     RED
    0.06
    ximity
    0.06
     ?>'
    0.06
    Act Density 0.031%

    No Known Activations