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

    Neuronpedia

    INDEX
    Explanations

    project report thesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nuanced
    0.42
     unpack
    0.40
     tweet
    0.38
     tweaks
    0.38
     ट्वीट
    0.38
    inander
    0.38
    Tweets
    0.38
     retweet
    0.37
     Tweets
    0.37
    āng
    0.37
    POSITIVE LOGITS
     report
    0.80
     project
    0.80
     thesis
    0.78
    report
    0.77
    Objectives
    0.77
     Report
    0.76
     objectives
    0.76
    Project
    0.75
    thesis
    0.75
     REPORT
    0.72
    Act Density 0.019%

    No Known Activations