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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Businesses
    0.76
     adoptive
    0.68
     charset
    0.67
     unn
    0.65
     hail
    0.64
     confession
    0.63
     bonds
    0.62
    мит
    0.62
     extra
    0.61
     Secrets
    0.61
    POSITIVE LOGITS
    מ
    1.05
    נ
    0.98
    ב
    0.92
    вяза
    0.91
    ר
    0.90
    ע
    0.89
    そして
    0.87
    ح
    0.84
     Azores
    0.84
    ޏ
    0.83
    Act Density 0.000%

    No Known Activations