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

    Neuronpedia

    INDEX
    Explanations

    technical jargon related to neural networks and their operations

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

    before "pool" or related to activation functions

    np_acts-logits-general · gemini-2.0-flash

    activation functions and pooling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    windowFixed
    -0.61
     AssemblyCulture
    -0.61
    CodedInputStream
    -0.58
     Roskov
    -0.51
    TagMode
    -0.50
     QName
    -0.50
    ----</
    -0.49
    Rohy
    -0.48
    IUrlHelper
    -0.47
    ValueStyle
    -0.46
    POSITIVE LOGITS
     activation
    0.71
     relu
    0.67
     Activation
    0.66
     layer
    0.65
    activation
    0.60
    Layer
    0.60
    Activation
    0.60
     Audiodateien
    0.60
    activate
    0.59
    激活
    0.59
    Act Density 0.201%

    No Known Activations