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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     enforced
    1.08
    𝐥
    1.07
    いますが
    1.07
     temporally
    1.06
    たま
    1.04
    utiérrez
    1.02
    三个
    1.02
     нажмите
    1.02
     eloku
    1.02
    近年
    1.02
    POSITIVE LOGITS
    ر
    1.67
    ческое
    1.19
     rota
    1.14
     debajo
    1.12
     daraus
    1.12
     largura
    1.12
     perkara
    1.12
     multiplicação
    1.11
     Wasch
    1.10
    шой
    1.10
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.