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

    Neuronpedia

    INDEX
    Explanations

    insurance coverage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Converter
    -0.07
     Tried
    -0.07
    主人
    -0.06
    ancock
    -0.06
     tyr
    -0.06
     gastr
    -0.06
     Stations
    -0.06
    анной
    -0.06
    ân
    -0.06
    Door
    -0.06
    POSITIVE LOGITS
    λεί
    0.07
    YL
    0.07
    relative
    0.07
     irrelevant
    0.07
    Static
    0.06
    -p
    0.06
     documents
    0.06
    statistics
    0.06
     sounded
    0.06
    bundle
    0.06
    Act Density 0.007%

    No Known Activations