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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    >'
    1.38
     общий
    1.30
    onka
    1.23
     harassment
    1.18
     строение
    1.18
     rinsing
    1.16
    পার
    1.14
     хоть
    1.13
     shepherd
    1.13
    เลือด
    1.12
    POSITIVE LOGITS
    費
    1.35
     això
    1.31
     entitle
    1.23
     prefer
    1.22
     deserve
    1.22
     geng
    1.21
    unshift
    1.19
    数量
    1.18
     seus
    1.16
     espaços
    1.16
    Act Density 0.000%

    No Known Activations