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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ম্ম
    0.82
    тися
    0.81
     possibili
    0.80
     conversa
    0.79
     reaping
    0.78
     blushing
    0.78
    eward
    0.78
    蚪
    0.77
     фев
    0.76
     neve
    0.73
    POSITIVE LOGITS
    ية
    1.02
    4
    0.82
     Вы
    0.80
    3
    0.80
    IP
    0.79
     Asimismo
    0.76
    INY
    0.75
    9
    0.75
    ﻟ
    0.75
    링
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.