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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     estima
    0.39
    rish
    0.38
    nish
    0.38
    throp
    0.37
     discour
    0.37
     osv
    0.37
     czter
    0.37
     estim
    0.36
     researches
    0.36
     profiss
    0.36
    POSITIVE LOGITS
    মূলক
    0.44
     ניתן
    0.42
    Í
    0.42
     Prü
    0.41
    谜
    0.41
     הא
    0.40
    ה
    0.40
     Void
    0.40
     পৃথক
    0.40
     నిర్మాణ
    0.39
    Act Density 0.000%

    No Known Activations