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

    Neuronpedia

    INDEX
    Explanations

    below

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Zhang
    -0.06
    Editing
    -0.06
     wx
    -0.06
    rows
    -0.06
     облич
    -0.06
    Infrastructure
    -0.06
    Amazon
    -0.06
    ungan
    -0.06
     fragmentManager
    -0.06
    Hel
    -0.06
    POSITIVE LOGITS
    _down
    0.07
    auen
    0.06
    (AP
    0.06
     cached
    0.06
     defe
    0.06
     merc
    0.06
     Loài
    0.06
    最后
    0.06
    ,-
    0.06
     Gros
    0.06
    Act Density 0.014%

    No Known Activations