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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     fonctionnent
    0.44
    ?')
    0.44
     funzionamento
    0.42
    ométrique
    0.41
     стоимости
    0.40
    हित
    0.39
    లతో
    0.39
    }.",
    0.39
     funcional
    0.39
    ंधन
    0.38
    POSITIVE LOGITS
    roots
    0.44
     Wurzel
    0.42
     J
    0.41
     hide
    0.40
    Roots
    0.39
     roots
    0.38
     talked
    0.38
     dipping
    0.38
     Mad
    0.38
    ামা
    0.37
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.