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

    Neuronpedia

    INDEX
    Explanations

    GPT model generations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ہوجائے
    0.42
     एखाद्या
    0.42
     centuries
    0.41
     guérison
    0.41
    种植
    0.41
     patho
    0.41
    淔
    0.41
     zodat
    0.40
     fiddle
    0.40
     hoti
    0.40
    POSITIVE LOGITS
     OpenAI
    1.00
     flagship
    0.95
     models
    0.93
     GPT
    0.89
     latest
    0.83
     successor
    0.83
     모델
    0.82
     Models
    0.81
     newer
    0.80
     terbaru
    0.80
    Act Density 0.112%

    No Known Activations