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

    Neuronpedia

    INDEX
    Explanations

    ned

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ledig
    -0.07
     blijft
    -0.07
     व्यक्त
    -0.07
     queda
    -0.07
     simplifies
    -0.07
    िने
    -0.07
    Invariant
    -0.07
    Increment
    -0.07
    गा
    -0.07
    ेप
    -0.07
    POSITIVE LOGITS
     Sympathy
    0.08
    ои
    0.08
    	printf
    0.08
     проис
    0.08
    品質
    0.07
     Shame
    0.07
    	define
    0.07
    .printf
    0.07
     основные
    0.07
    ызы
    0.07
    Act Density 0.001%

    No Known Activations