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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    0.43
    8
    0.29
    7
    0.29
    3
    0.28
    ↵↵
    0.27
    4
    0.27
    6
    0.25
       
    0.25
     J
    0.24
     दो
    0.24
    POSITIVE LOGITS
     በሽታ
    0.29
    汅
    0.27
     malattie
    0.27
    នៅ
    0.26
     délai
    0.26
     toxic
    0.25
    病情
    0.25
     cervello
    0.25
    s
    0.25
    会导致
    0.25
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.