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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wonderfully
    -0.09
     hallmark
    -0.09
     fundamentals
    -0.09
     Fundamentals
    -0.09
    Basics
    -0.08
     remarkably
    -0.08
    、と
    -0.08
     markedly
    -0.08
     весьма
    -0.08
     निम
    -0.08
    POSITIVE LOGITS
    数组
    0.09
    /ms
    0.08
     */↵
    0.08
     iter
    0.08
     splitted
    0.07
    0.07
     veuillez
    0.07
    ...")↵
    0.07
    Dubai
    0.07
    asd
    0.07
    Act Density 0.080%
    No Known Activations