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

    Neuronpedia

    INDEX
    Explanations

    blast beats, blush-pink, from olive oil

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    崢
    0.98
    AssetsRequest
    0.97
    全新
    0.97
     innovative
    0.96
     predefined
    0.92
     funcionalidad
    0.92
    坚定
    0.92
    创新
    0.91
     geospatial
    0.90
    IoT
    0.90
    POSITIVE LOGITS
     ().
    1.62
    .*
    1.55
    .
    1.54
    .(
    1.47
     (!
    1.46
    .;
    1.44
    .)
    1.43
    ;
    1.43
     (
    1.41
    ).
    1.39
    Act Density 0.001%

    No Known Activations