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

    Neuronpedia

    INDEX
    Explanations

    layout and admin code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AttributedString
    0.39
    좔
    0.39
     للف
    0.38
     Owl
    0.37
     Owls
    0.36
    ন্ত্রণ
    0.36
     Structured
    0.36
    revenue
    0.35
     Revenue
    0.35
    yield
    0.35
    POSITIVE LOGITS
     ADMINISTRATIVE
    0.37
     graf
    0.36
     afterthought
    0.36
     ADMIN
    0.35
    夻
    0.35
     dissipate
    0.34
     accessory
    0.33
     Graf
    0.33
     бога
    0.33
     incompatibility
    0.33
    Act Density 0.000%

    No Known Activations