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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Phillips
    -0.06
    武器
    -0.06
     Merk
    -0.06
    工业
    -0.06
    _lift
    -0.06
     Khan
    -0.06
     Bor
    -0.06
     toilets
    -0.06
     shl
    -0.06
     HANDLE
    -0.06
    POSITIVE LOGITS
    .tpl
    0.07
     accountant
    0.07
     Oracle
    0.07
    -cur
    0.07
     книги
    0.07
    alleries
    0.06
    koneksi
    0.06
    .Compile
    0.06
    _________________↵↵
    0.06
     ({↵
    0.06
    Act Density 0.010%

    No Known Activations