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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Crypto
    0.83
     Crypto
    0.74
    ليز
    0.72
    نر
    0.72
    बरे
    0.72
     pector
    0.72
     apparaître
    0.71
    lauf
    0.71
     überall
    0.69
     నమో
    0.69
    POSITIVE LOGITS
    ны
    0.73
    ="...">
    0.71
    ">
    0.70
    щаем
    0.68
     dyd
    0.68
    вшая
    0.66
     kepentingan
    0.66
    ה
    0.66
    щение
    0.65
    ter
    0.63
    Act Density 0.000%

    No Known Activations