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

    Neuronpedia

    INDEX
    Explanations

    terms related to convolutional neural network operations and their features

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

    feature map gradients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lenker
    -0.52
    лтамалар
    -0.50
    RectangleBorder
    -0.50
     mergeFrom
    -0.49
     <<<<<<<<<<<<<<
    -0.48
     initComponents
    -0.47
    下载附件
    -0.47
    RTEE
    -0.45
    帖最后由
    -0.44
     kaarangay
    -0.44
    POSITIVE LOGITS
    convolution
    0.49
     Conv
    0.48
    Convolution
    0.45
    Muslims
    0.44
     Ophthalmology
    0.43
    Conv
    0.42
     Convolution
    0.42
     setImage
    0.41
    Married
    0.40
     convolutional
    0.40
    Act Density 0.037%

    No Known Activations