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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    al
    1.11
    opathy
    1.05
    auty
    1.02
    ipedia
    1.01
    obot
    1.01
    auce
    1.00
    arine
    1.00
    vered
    0.97
    otry
    0.95
    ynth
    0.95
    POSITIVE LOGITS
     seperti
    1.50
     यानी
    1.44
     berupa
    1.41
     मसलन
    1.41
     म्हणजेच
    1.38
     Misalnya
    1.37
    比如
    1.36
     yakni
    1.31
     مثل
    1.30
     răng
    1.29
    Act Density 0.263%

    No Known Activations