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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    (
    0.83
    見
    0.75
    ме
    0.73
    se
    0.69
    aner
    0.69
    ta
    0.69
    и
    0.68
    《
    0.67
    מ
    0.66
    ne
    0.65
    POSITIVE LOGITS
     baterías
    1.02
     hetzelfde
    1.00
     এছাড়াও
    0.99
     saddhim
    0.95
     истины
    0.91
    وه
    0.90
     batas
    0.90
     eléct
    0.90
     türlü
    0.89
    нические
    0.88
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.