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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ilig
    0.53
     नव्ह
    0.51
    ုန်
    0.51
    ศัก
    0.48
    ையில்
    0.47
    ்தான்
    0.47
    onesia
    0.46
     डीएल
    0.46
    ılması
    0.45
    वान
    0.44
    POSITIVE LOGITS
    ARR
    0.46
    ERG
    0.46
     rejects
    0.43
    Released
    0.43
     autor
    0.43
     unobstructed
    0.43
     emitted
    0.42
    कर्मा
    0.42
    ABEL
    0.42
    盖
    0.42
    Act Density 0.001%

    No Known Activations