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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hann
    -0.08
     BitSet
    -0.08
     cyclist
    -0.07
    <c
    -0.07
     vines
    -0.07
    延期
    -0.07
     nitrogen
    -0.06
    保鲜
    -0.06
     DIFF
    -0.06
    Forgery
    -0.06
    POSITIVE LOGITS
    uitable
    0.07
    什么样的
    0.07
     setup
    0.07
    解析
    0.07
    .Ex
    0.07
    рук
    0.07
    !!!↵
    0.07
     pacman
    0.07
    _gradient
    0.07
    menu
    0.06
    Act Density 0.001%

    No Known Activations