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

    Neuronpedia

    INDEX
    Explanations

    general support content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рукту
    -0.07
    Sha
    -0.06
     الغ
    -0.06
    webpack
    -0.06
    iếu
    -0.06
    vinces
    -0.06
    notEmpty
    -0.06
    _ring
    -0.06
    ensen
    -0.06
    .vertical
    -0.06
    POSITIVE LOGITS
    ější
    0.06
     وأن
    0.06
     Eigen
    0.06
     Consum
    0.06
     klar
    0.06
     Lemon
    0.06
     انتخاب
    0.06
     �
    0.06
     sermon
    0.06
    (mu
    0.05
    Act Density 0.089%

    No Known Activations