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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    на
    1.23
    ल
    1.22
    ができる
    1.16
    什么
    1.04
    が多く
    1.02
    ingly
    1.01
    스의
    1.01
    ipelago
    0.98
    できる
    0.97
     visto
    0.97
    POSITIVE LOGITS
    fe
    1.07
    féle
    1.01
                                 
    0.96
    من
    0.96
    کلی
    0.95
    ៧
    0.95
    Institution
    0.94
    犹如
    0.94
    SLASH
    0.92
    ant
    0.91
    Act Density 0.027%

    No Known Activations