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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seab
    -0.07
     Ngoài
    -0.07
    .executor
    -0.07
     fled
    -0.06
     pirates
    -0.06
    >"
↵
    -0.06
    Ed
    -0.06
    uencia
    -0.06
    ộ
    -0.06
     celib
    -0.06
    POSITIVE LOGITS
     features
    0.07
     документа
    0.07
    [length
    0.07
    rc
    0.06
    pressions
    0.06
     -------
    0.06
    lahoma
    0.06
    \t
    0.06
     losing
    0.06
     cms
    0.06
    Act Density 0.001%

    No Known Activations