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

    Neuronpedia

    INDEX
    Explanations

    social media ui elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myogenic
    0.47
     mengalami
    0.47
     kombin
    0.46
     essen
    0.45
     reac
    0.45
    نه
    0.45
    櫛
    0.44
     ople
    0.44
     Brokers
    0.44
     plot
    0.43
    POSITIVE LOGITS
    carrito
    0.49
    ítez
    0.46
     चिंता
    0.45
     দায়িত্ব
    0.43
    ("\
    0.42
    喜欢
    0.42
    孙
    0.41
    tarea
    0.41
    喜欢的
    0.41
    ills
    0.40
    Act Density 0.001%

    No Known Activations