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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     UDP
    1.37
    /...
    1.27
    Dup
    1.24
    にかく
    1.24
     overruling
    1.24
    alho
    1.23
    iin
    1.23
     kroner
    1.22
     overuse
    1.22
    ي
    1.20
    POSITIVE LOGITS
    ent
    1.09
    шы
    0.96
    மை
    0.94
    凿
    0.93
    म्मत
    0.93
    ंसक
    0.90
     رشته
    0.89
    ть
    0.89
    まま
    0.88
    ating
    0.87
    Act Density 0.000%

    No Known Activations