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

    Neuronpedia

    INDEX
    Explanations

    registering models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Beauty
    0.38
    出于
    0.37
    kara
    0.37
     Ian
    0.36
     draft
    0.36
    ваи
    0.36
    ";
    0.35
    erset
    0.35
     독
    0.35
     garder
    0.35
    POSITIVE LOGITS
     models
    0.80
     Models
    0.77
    Models
    0.70
     modèles
    0.70
     modelos
    0.70
    models
    0.68
     MODELS
    0.68
     моделей
    0.66
     modelli
    0.66
     модели
    0.62
    Act Density 0.000%

    No Known Activations