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

    Neuronpedia

    INDEX
    Explanations

    body parts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    doctrine
    -0.07
    connection
    -0.06
    getModel
    -0.06
     risen
    -0.06
    SubMenu
    -0.06
     تعیین
    -0.06
    �
    -0.06
     CMS
    -0.06
     مار
    -0.06
    Serializer
    -0.06
    POSITIVE LOGITS
    」の
    0.07
     пенс
    0.06
    �
    0.06
    蘭
    0.06
    ře
    0.06
    	rb
    0.06
    ******↵↵
    0.06
    執
    0.06
    .USER
    0.06
    .splitext
    0.06
    Act Density 0.023%

    No Known Activations