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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    natal
    0.83
    }}}}$
    0.81
    купно
    0.79
    0.78
    noc
    0.76
    তীশ
    0.73
    рина
    0.71
    च्चय
    0.70
    }}=(
    0.68
    ாளர்கள்
    0.67
    POSITIVE LOGITS
     fasse
    0.97
    で
    0.97
     alumnos
    0.96
     faisant
    0.90
     classe
    0.89
     ambiente
    0.89
     ruim
    0.88
     istilah
    0.88
     vamos
    0.86
    에서
    0.86
    Act Density 0.000%

    No Known Activations