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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    스의
    0.62
    ^{*}}\
    0.62
    ૦
    0.61
     ဆို
    0.60
     теркәлү
    0.59
     අධ
    0.59
     சிறிய
    0.59
    trashItem
    0.57
    욌
    0.57
     أم
    0.57
    POSITIVE LOGITS
    an
    0.95
    ↵
    0.91
    ل
    0.76
    ar
    0.73
    ,
    0.72
    on
    0.70
    in
    0.69
    at
    0.68
    le
    0.68
    el
    0.66
    Act Density 6.848%

    No Known Activations