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

    Neuronpedia

    INDEX
    Explanations

    ization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     çevre
    -0.06
     تعد
    -0.06
    iedade
    -0.06
     relig
    -0.06
    -letter
    -0.06
     NUMBER
    -0.06
     зб
    -0.05
     Dre
    -0.05
    俺は
    -0.05
     खड
    -0.05
    POSITIVE LOGITS
    _cum
    0.08
    (view
    0.07
     PERF
    0.07
     wear
    0.07
    .Tests
    0.07
     advantage
    0.07
    الی
    0.07
     basics
    0.07
    .Sequence
    0.06
     sécur
    0.06
    Act Density 0.000%

    No Known Activations