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

    Neuronpedia

    INDEX
    Explanations

    terms related to convolutional operations and architectures

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

    conviction or convolution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     financière
    -0.42
     Hauteur
    -0.42
     Ärz
    -0.39
     ouder
    -0.39
     Países
    -0.38
     voici
    -0.38
     Asher
    -0.38
     Staates
    -0.38
     Füßen
    -0.37
     pájaros
    -0.37
    POSITIVE LOGITS
    conv
    2.36
     conv
    2.33
     Conv
    2.02
    Conv
    1.88
    CONV
    1.80
     CONV
    1.70
     convolution
    1.34
     convulsions
    1.25
     Convolution
    1.15
     convo
    1.10
    Act Density 0.014%

    No Known Activations