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

    Neuronpedia

    INDEX
    Explanations

    legality of content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TypeError
    0.43
     playerData
    0.41
     bullying
    0.40
    asser
    0.39
     precautionary
    0.39
     criteria
    0.39
     wilfully
    0.38
     padding
    0.38
     panic
    0.38
     criteri
    0.38
    POSITIVE LOGITS
     legal
    2.05
    legal
    1.94
    法律
    1.93
     कानूनी
    1.89
    Legal
    1.85
     법
    1.80
     legales
    1.77
     Legal
    1.76
     legais
    1.74
     LEGAL
    1.66
    Act Density 0.027%

    No Known Activations