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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     நடித்த
    0.64
    करिता
    0.53
    igated
    0.52
    ずつ
    0.52
     فريبي
    0.51
     требуется
    0.51
     podrá
    0.50
     watery
    0.50
    યર
    0.50
    <unused2037>
    0.50
    POSITIVE LOGITS
    2
    0.53
     is
    0.52
    kung
    0.48
    W
    0.47
    ’
    0.47
    Formula
    0.46
    ensus
    0.46
    Ciao
    0.46
    雏
    0.46
     dividend
    0.45
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.