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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     शू
    0.72
     fer
    0.69
     blew
    0.68
     punch
    0.68
     gravity
    0.68
    -(\
    0.67
    λο
    0.67
     ate
    0.66
    eto
    0.66
     gra
    0.66
    POSITIVE LOGITS
    ﻱ
    0.68
     دیتی
    0.67
    Origins
    0.66
    middels
    0.63
     يتعلق
    0.63
     コス
    0.62
    reonine
    0.62
     oes
    0.62
    હિતી
    0.62
    obedience
    0.62
    Act Density 0.000%

    No Known Activations