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

    Neuronpedia

    INDEX
    Explanations

    mortgage packages, laundry detergent, housing structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     both
    0.45
    魍
    0.41
     previously
    0.40
     starting
    0.39
    Both
    0.38
    every
    0.38
     incor
    0.37
     unless
    0.37
     vertex
    0.37
     complete
    0.37
    POSITIVE LOGITS
     Myths
    0.48
    ização
    0.46
     Podcasts
    0.46
     ransomware
    0.46
     sponsorships
    0.46
     internships
    0.46
     सलाहकार
    0.45
     بیاکتنې
    0.45
     Pricing
    0.44
     Diaries
    0.43
    Act Density 0.108%

    No Known Activations