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

    Neuronpedia

    INDEX
    Explanations

    Number one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     up
    -1.02
    up
    -0.73
    Up
    -0.69
     Up
    -0.69
    IntoConstraints
    -0.66
    :]:
    -0.57
     saj
    -0.55
    Até
    -0.54
    起
    -0.53
    /**
    -0.51
    POSITIVE LOGITS
    rawDesc
    0.62
     ostavi
    0.61
     المعيارى
    0.60
    PullParser
    0.59
    InteropServices
    0.58
    Šaltiniai
    0.58
    ictwo
    0.57
     szól
    0.57
    ">//
    0.57
     fubject
    0.57
    Act Density 1.486%

    No Known Activations