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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    $
    1.03
    <sub>
    1.02
    iable
    1.02
    \(
    0.98
    Unicode
    0.98
    (
    0.92
    काय
    0.91
    IGNORE
    0.90
    $\
    0.88
    o
    0.87
    POSITIVE LOGITS
     tiszt
    1.34
     potencia
    1.32
     Juillet
    1.32
     matahari
    1.31
     Schönheit
    1.27
    թ
    1.27
     sejumlah
    1.26
    <unused1105>
    1.25
     sejarah
    1.25
     prestasi
    1.24
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.