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

    Neuronpedia

    INDEX
    Explanations

    Euclidean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Est
    -0.07
    踊跃
    -0.07
    峘
    -0.07
     eval
    -0.07
    瓶颈
    -0.06
    olving
    -0.06
     mối
    -0.06
    claimed
    -0.06
    ertools
    -0.06
    各方
    -0.06
    POSITIVE LOGITS
    .Since
    0.09
     posting
    0.07
    ży
    0.07
    (Layout
    0.07
    .Generic
    0.07
    -Nazi
    0.07
    ując
    0.07
     Tek
    0.07
    	HANDLE
    0.07
    ・・・↵↵
    0.07
    Act Density 0.001%

    No Known Activations