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

    Neuronpedia

    INDEX
    Explanations

    world

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Collapse
    -0.07
     SECTION
    -0.07
     pll
    -0.07
     FIRST
    -0.07
    modele
    -0.07
    �
    -0.07
    寝
    -0.07
     onResponse
    -0.07
    ﻭ
    -0.07
    _Total
    -0.07
    POSITIVE LOGITS
    汉子
    0.08
    ską
    0.07
     guarded
    0.07
    ).
↵
    0.07
    的女孩
    0.07
    irting
    0.07
    esso
    0.07
    -world
    0.07
    文件
    0.07
     preacher
    0.07
    Act Density 0.005%

    No Known Activations