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

    Neuronpedia

    INDEX
    Explanations

    `that` / `with` / `is`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     razie
    0.50
    кость
    0.48
    を行い
    0.47
    ipping
    0.47
     เพิ่ม
    0.47
     добиться
    0.47
    assertEqual
    0.46
    bringing
    0.46
    если
    0.45
    और
    0.45
    POSITIVE LOGITS
     größer
    0.57
     niedr
    0.55
     whose
    0.53
     belonged
    0.53
     insufficiently
    0.52
     kuten
    0.52
     diagnosed
    0.52
     tenían
    0.51
     belong
    0.50
     olmayan
    0.50
    Act Density 0.020%

    No Known Activations