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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    oretically
    0.79
    edian
    0.55
    ൊന്ന
    0.55
     नेहमी
    0.54
     ஆவார்
    0.53
    гат
    0.53
    ”、
    0.51
    ូច
    0.51
    ˆ
    0.51
    loir
    0.51
    POSITIVE LOGITS
     this
    5.75
    this
    5.46
     هذه
    5.28
     these
    5.19
     هذا
    5.17
     acest
    5.15
     этого
    5.11
     này
    5.10
     questa
    5.04
     этой
    5.00
    Act Density 5.081%

    No Known Activations