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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Spring
    -0.07
     }]);↵
    -0.07
     созд
    -0.07
    -↵↵
    -0.07
    hexdigest
    -0.07
    "))
↵
    -0.06
     skulle
    -0.06
     lug
    -0.06
    	atomic
    -0.06
    נסי
    -0.06
    POSITIVE LOGITS
    떳
    0.07
    选定
    0.07
    哔
    0.07
    穿着
    0.06
    偉
    0.06
     Kra
    0.06
    的照片
    0.06
    (bin
    0.06
    祋
    0.06
     leggings
    0.06
    Act Density 0.017%

    No Known Activations