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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     plough
    0.69
     adored
    0.68
    ר
    0.67
     griech
    0.66
     reins
    0.65
    "":
    0.64
     grec
    0.64
    "،
    0.63
    서
    0.63
     divorced
    0.62
    POSITIVE LOGITS
     expressões
    0.95
    ্পনিক
    0.91
    ità
    0.84
    äck
    0.82
    ênio
    0.81
    afar
    0.80
    icità
    0.80
     versões
    0.79
    éfonos
    0.79
    änä
    0.79
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.