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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ijo
    -0.07
    +\
    -0.06
    Sketch
    -0.06
     pertaining
    -0.06
     الأرض
    -0.06
    percent
    -0.06
     мик
    -0.06
    ��
    -0.06
     scheme
    -0.06
     work
    -0.06
    POSITIVE LOGITS
    Dating
    0.07
    Msg
    0.07
    fort
    0.07
    Course
    0.06
    -Oct
    0.06
    i�
    0.06
    collectionView
    0.06
    /apple
    0.06
     настоя
    0.06
    .wordpress
    0.06
    Act Density 0.054%

    No Known Activations