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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    keiten
    1.97
    ت
    1.96
    s
    1.79
    ἷ
    1.75
    ీ
    1.74
    يات
    1.73
     giants
    1.72
    юк
    1.68
     intervention
    1.67
     interventions
    1.66
    POSITIVE LOGITS
    РА
    1.90
     gern
    1.85
     gerne
    1.84
    ব
    1.79
    р
    1.78
    вто
    1.70
    мл
    1.66
    Vous
    1.63
    ۡ
    1.62
    datos
    1.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.