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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ❘
    0.55
    ]
    0.55
    ],
    0.54
     criminal
    0.54
    ]|
    0.51
    è
    0.50
    ̣
    0.50
    athlon
    0.50
     Imported
    0.50
     artic
    0.49
    POSITIVE LOGITS
    슘
    0.52
    म्या
    0.51
    うまく
    0.49
    תר
    0.49
    جاج
    0.49
    abhar
    0.48
    ెక్టర్
    0.48
    漂
    0.48
    рыя
    0.47
     antennis
    0.47
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.