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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     kanssa
    0.91
    częściej
    0.87
     começa
    0.86
     mesma
    0.85
     работает
    0.85
    лы
    0.84
    łego
    0.82
     sobretudo
    0.82
     поколения
    0.80
     года
    0.80
    POSITIVE LOGITS
    י
    0.88
    IK
    0.85
     Emirati
    0.82
    א
    0.77
    台湾
    0.77
    泰国
    0.76
     Brunei
    0.74
    ו
    0.74
     Challenges
    0.73
    ע
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.