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

    Neuronpedia

    INDEX
    Explanations

    phrases like "get this over with"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    to
    0.57
    টসম্যান
    0.56
    OrEqualTo
    0.51
    Marc
    0.50
    ν
    0.49
     Pengembangan
    0.49
    aft
    0.49
    Neill
    0.49
    butanol
    0.48
    Concini
    0.48
    POSITIVE LOGITS
     দু
    0.56
     você
    0.56
     janeiro
    0.54
     你
    0.52
     bạn
    0.52
     spécialement
    0.51
    ك
    0.51
    您
    0.49
     queste
    0.49
    电脑
    0.49
    Act Density 0.000%

    No Known Activations