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

    Neuronpedia

    INDEX
    Explanations

    model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DataSet
    -0.07
    	mem
    -0.07
     didFinish
    -0.07
     goose
    -0.07
     Anonymous
    -0.06
    Consumer
    -0.06
    βι
    -0.06
     gauss
    -0.06
     يست
    -0.06
    tas
    -0.06
    POSITIVE LOGITS
     модели
    0.07
     models
    0.07
     model
    0.07
     modelos
    0.07
     модель
    0.06
    reset
    0.06
    рей
    0.06
     freelancer
    0.06
     modelo
    0.06
     автомоб
    0.06
    Act Density 0.014%

    No Known Activations