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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     божомолу
    0.89
     inclui
    0.87
     proporcional
    0.86
     происходит
    0.86
     üçün
    0.84
    ꯋ
    0.84
     eqn
    0.83
    য়ান
    0.82
    elwv
    0.82
    ังกฤษ
    0.82
    POSITIVE LOGITS
    ans
    0.82
    ors
    0.79
    sa
    0.74
    us
    0.72
    ries
    0.72
    ion
    0.71
    opens
    0.71
    س
    0.70
    ers
    0.70
    ure
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.