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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     confertim
    0.91
    ૪
    0.83
    ATIONS
    0.83
    പ്പിച്ചി
    0.82
    criminals
    0.82
     ഇല്ല
    0.80
    ocate
    0.80
     coordinators
    0.79
    шком
    0.79
    ７
    0.79
    POSITIVE LOGITS
     Kitchen
    0.74
     पैर
    0.70
    Kitchen
    0.70
     läht
    0.65
     इसकी
    0.64
    µ
    0.64
     ab
    0.63
    น่า
    0.63
     त्यात
    0.63
     இதில்
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.