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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    은
    0.61
    姓
    0.60
    서
    0.59
    ↵↵
    0.58
    ↵↵↵
    0.58
    กับ
    0.57
    见
    0.57
    见的
    0.55
    krb
    0.54
    ↵
    0.54
    POSITIVE LOGITS
    ufieurs
    0.73
     einen
    0.69
     الذين
    0.67
    ທີ່ມີ
    0.67
     linguaggio
    0.66
     получи
    0.66
     autres
    0.65
     فيديو
    0.65
     introduit
    0.65
    োধনী
    0.65
    Act Density 0.007%

    No Known Activations