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

    Neuronpedia

    INDEX
    Explanations

    br prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     મેળ
    0.47
    ოლოგი
    0.47
     осуществляется
    0.44
    㞰
    0.44
    ensuche
    0.43
     Пів
    0.42
    嚧
    0.42
    靘
    0.42
    非常
    0.41
     забезпе
    0.41
    POSITIVE LOGITS
    rrrr
    0.60
    Br
    0.58
    r
    0.58
    pr
    0.57
    br
    0.56
    iss
    0.54
    att
    0.54
    agment
    0.53
    ud
    0.53
     Br
    0.53
    Act Density 0.027%

    No Known Activations