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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    $-
    0.96
     lore
    0.96
    uments
    0.94
     termination
    0.91
     Termination
    0.90
     ә
    0.90
     اوقات
    0.89
    ద్ధ
    0.88
     gloria
    0.87
    вить
    0.87
    POSITIVE LOGITS
    瑗
    1.02
     ನಂತರ
    1.00
     insuffis
    0.92
     Ramadan
    0.85
    ťaž
    0.85
    Depois
    0.83
    <unused499>
    0.83
    ljeni
    0.83
    挫
    0.81
    楽天
    0.81
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.