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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     overriding
    0.40
     chở
    0.36
    ż
    0.36
    ਿਕ
    0.35
    ktor
    0.35
    บาย
    0.34
     disabling
    0.33
     ulter
    0.33
    glad
    0.33
    押し
    0.32
    POSITIVE LOGITS
     Edith
    0.34
     Warwick
    0.31
    ڦ
    0.31
     Flower
    0.31
    ἥ
    0.30
     Surrounded
    0.30
     Griff
    0.29
     Segu
    0.29
     Local
    0.28
    MUN
    0.28
    Act Density 0.786%

    No Known Activations