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

    Neuronpedia

    INDEX
    Explanations

    inviting research submissions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Linkedin
    0.45
     Linkedin
    0.44
    偻
    0.42
     qtd
    0.42
    Youtube
    0.41
     Youtube
    0.39
    LinkedIn
    0.39
     अश्विन
    0.38
     मार्ग
    0.38
    ဵ
    0.38
    POSITIVE LOGITS
     papers
    1.04
     submissions
    0.96
    Papers
    0.92
     Papers
    0.91
    papers
    0.90
     manuscripts
    0.80
    submissions
    0.74
     submit
    0.73
     submitted
    0.73
     topics
    0.70
    Act Density 0.010%

    No Known Activations