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

    Neuronpedia

    INDEX
    Explanations

    `exec` or `less` followed by specific sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    1.95
     పాటు
    1.63
     convolutional
    1.57
    клад
    1.54
    भरा
    1.53
    र
    1.53
     dawned
    1.52
     siguientes
    1.49
     passwd
    1.48
    работ
    1.48
    POSITIVE LOGITS
    س
    1.76
     наличи
    1.61
    де
    1.48
    de
    1.47
    𝑪
    1.47
    definite
    1.47
     disparate
    1.45
     groupings
    1.44
    с
    1.43
    ities
    1.42
    Act Density 0.027%

    No Known Activations