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

    Neuronpedia

    INDEX
    Explanations

    Court submission dates

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	UObject
    -0.07
    "It
    -0.07
    (Yii
    -0.07
    😑
    -0.07
    �
    -0.07
     "<?
    -0.07
    🇶
    -0.07
     så
    -0.07
     ComponentFixture
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    重启
    0.08
     Policy
    0.07
    ),↵↵
    0.07
    `,
    0.07
    籌
    0.07
    一则
    0.07
    wnd
    0.06
    管理层
    0.06
    Rol
    0.06
    هن
    0.06
    Act Density 0.003%

    No Known Activations