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

    Neuronpedia

    INDEX
    Explanations

    terms related to matrix structure and properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding "padding," "boxes," or abbreviations

    np_acts-logits-general · gemini-2.0-flash

    left padding and boxes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AutoScaleMode
    -0.78
    Vidite
    -0.74
    IUrlHelper
    -0.71
    RenderAtEndOf
    -0.69
     createState
    -0.66
    
    -0.66
    setVerticalGroup
    -0.64
    ίδι
    -0.59
    WriteBarrier
    -0.59
     insuffisamment
    -0.56
    POSITIVE LOGITS
     ComVisible
    0.66
     चीज़ों
    0.55
     maupun
    0.55
    رشف
    0.53
    HomeAsUp
    0.52
    GeoNames
    0.52
    msgSender
    0.52
    الحياه
    0.51
    TestBed
    0.50
    setBold
    0.48
    Act Density 0.647%

    No Known Activations