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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     مقاب
    0.95
     nadie
    0.94
     combatir
    0.93
    วัสดี
    0.88
     никто
    0.87
     dando
    0.86
     dürfen
    0.86
     ebenso
    0.85
    ✽
    0.84
     viven
    0.84
    POSITIVE LOGITS
    t
    1.37
    า
    1.03
    days
    0.99
    j
    0.98
    stones
    0.96
    ح
    0.94
    marca
    0.93
    town
    0.93
     espace
    0.92
    rale
    0.91
    Act Density 0.000%

    No Known Activations