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

    Neuronpedia

    INDEX
    Explanations

    championship belt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     누구
    0.62
     যুক্তি
    0.61
     necessidades
    0.59
     насе
    0.58
     xanth
    0.57
    ﻐ
    0.57
     народ
    0.57
     Каждый
    0.57
     ці
    0.57
     Sache
    0.57
    POSITIVE LOGITS
    )
    0.63
    ada
    0.55
    odes
    0.55
    id
    0.54
    ش
    0.53
    ק
    0.52
    class
    0.52
    iki
    0.50
    O
    0.49
    ik
    0.49
    Act Density 0.002%

    No Known Activations