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
     bour
    -0.07
     withd
    -0.06
    Sidebar
    -0.06
    oard
    -0.06
    ItemCount
    -0.06
     возникнов
    -0.06
    rani
    -0.06
     dakika
    -0.06
    ып
    -0.06
     Cumberland
    -0.06
    POSITIVE LOGITS
     relied
    0.07
    .Long
    0.07
    common
    0.07
     Bone
    0.06
    [layer
    0.06
    abcdefghijkl
    0.06
    意味
    0.06
    [it
    0.06
     tüm
    0.06
    lei
    0.06
    Act Density 0.000%

    No Known Activations