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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    EST
    0.80
     아니라
    0.79
     displaced
    0.73
    다
    0.73
    ↵
    0.71
    ])),
    0.69
    LINE
    0.69
     priorities
    0.68
     szá
    0.68
    =====
    0.66
    POSITIVE LOGITS
    ین
    1.12
    سی
    1.09
    رو
    0.98
    などの
    0.97
    ठभे
    0.96
     bekannte
    0.96
    سن
    0.95
    см
    0.95
     Они
    0.95
     انھوں
    0.95
    Act Density 0.008%

    No Known Activations