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
    amı
    -0.07
     teaches
    -0.07
    ateful
    -0.07
    ，全
    -0.07
    utas
    -0.07
    (stack
    -0.06
     IQueryable
    -0.06
    เจร
    -0.06
    TestFixture
    -0.06
    .Flush
    -0.06
    POSITIVE LOGITS
    ICTURE
    0.07
     TT
    0.06
    _p
    0.06
     رنگ
    0.06
    _is
    0.06
    ευ
    0.06
     Yi
    0.06
    Th
    0.06
     brackets
    0.06
    dart
    0.06
    Act Density 0.001%

    No Known Activations