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

    Neuronpedia

    INDEX
    Explanations

    Nebraska locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PK
    -0.07
    (mt
    -0.07
    (nums
    -0.07
    Flexible
    -0.07
     Grinder
    -0.07
    "/>↵↵
    -0.06
    ]);↵
    -0.06
    '];?>↵
    -0.06
     cake
    -0.06
    [D
    -0.06
    POSITIVE LOGITS
    �回
    0.07
    ها
    0.06
    าจ
    0.06
    	HANDLE
    0.06
    ่าส
    0.06
    dust
    0.06
    บาง
    0.06
    udded
    0.06
     ham
    0.06
     LOS
    0.06
    Act Density 0.009%

    No Known Activations