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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    บาด
    0.40
     _
    0.39
     Iwas
    0.38
    達
    0.37
     sanc
    0.36
    Code
    0.35
    بانی
    0.35
    нам
    0.35
    ండా
    0.35
    ิก
    0.34
    POSITIVE LOGITS
     टाइगर
    0.45
    킹
    0.43
     ننوت
    0.43
     യുവാ
    0.43
     किंग्स
    0.42
    दिग्ध
    0.42
    cheek
    0.42
    𝔰
    0.41
    Carolina
    0.41
    kat
    0.40
    Act Density 0.000%

    No Known Activations