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

    Neuronpedia

    INDEX
    Explanations

    scientific experiments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    选择
    -0.07
     Bread
    -0.07
     эти
    -0.07
     Кам
    -0.07
    lab
    -0.07
    ,r
    -0.07
    _RANDOM
    -0.07
     falsely
    -0.07
     Below
    -0.07
    ,C
    -0.06
    POSITIVE LOGITS
    \Auth
    0.06
     tapered
    0.06
     selv
    0.06
     mindful
    0.06
     miktar
    0.06
     conclus
    0.06
    ุท
    0.06
     Janeiro
    0.05
     Malay
    0.05
    Directions
    0.05
    Act Density 0.015%

    No Known Activations