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

    Neuronpedia

    INDEX
    Explanations

    writing and language use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    원은
    0.54
    рье
    0.51
     तीसरी
    0.50
     rutina
    0.49
     определения
    0.48
    وتي
    0.48
    RouterProvider
    0.47
     liderazgo
    0.46
    寘
    0.46
    粦
    0.46
    POSITIVE LOGITS
     synagogue
    0.48
    সংখ্যক
    0.47
     willingness
    0.47
     grasp
    0.46
     collaborative
    0.45
     bohemian
    0.44
     writers
    0.44
     grasped
    0.43
     words
    0.43
     gifted
    0.43
    Act Density 0.000%

    No Known Activations