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

    Neuronpedia

    INDEX
    Explanations

    missing or required values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gesetz
    0.38
    濃
    0.38
    ZERO
    0.37
     mortgages
    0.35
     embeds
    0.34
     compounds
    0.34
     valuation
    0.34
    )...
    0.34
     Locust
    0.34
     embed
    0.33
    POSITIVE LOGITS
    missing
    0.53
    Missing
    0.51
     Stands
    0.49
    referred
    0.49
     missing
    0.48
    stands
    0.46
     Missing
    0.46
     stands
    0.45
     tricky
    0.45
    Requires
    0.44
    Act Density 0.001%

    No Known Activations