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

    Neuronpedia

    INDEX
    Explanations

    around numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aug
    0.43
    勬
    0.38
     самоу
    0.38
     miel
    0.37
    //{
    0.37
     Komfort
    0.37
    oshima
    0.37
    乇
    0.37
    mht
    0.36
    ліся
    0.36
    POSITIVE LOGITS
     ആയി
    0.46
    箫
    0.39
     वार
    0.36
     punches
    0.35
    Attachments
    0.35
     Bend
    0.35
    attachments
    0.34
     গণতন্ত্র
    0.34
     ตัด
    0.34
     benzo
    0.34
    Act Density 0.038%

    No Known Activations