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

    Neuronpedia

    INDEX
    Explanations

    concepts and domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     debugShow
    0.39
    ieť
    0.38
    prova
    0.38
    দিগকে
    0.38
    দিগের
    0.38
    。（
    0.37
    दायक
    0.37
    mêmes
    0.37
    ராத
    0.37
     ശിഷ്യ
    0.36
    POSITIVE LOGITS
    -
    0.55
    /
    0.50
    ,
    0.47
    0.41
     and
    0.40
    iness
    0.39
     '
    0.36
     APIs
    0.36
     section
    0.36
    +
    0.35
    Act Density 0.074%

    No Known Activations