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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to feature extraction and representation in machine learning

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

    feature maps and extraction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Económica
    -0.71
    SharedDtor
    -0.65
     NavController
    -0.64
     arşivlendi
    -0.63
    хьтан
    -0.61
    umumkan
    -0.59
    CloseOperation
    -0.59
    +#+#
    -0.59
    berdayakan
    -0.57
    GIVEREF
    -0.56
    POSITIVE LOGITS
     Feature
    0.90
    feature
    0.89
    Feature
    0.84
     feature
    0.82
    features
    0.68
     FEATURE
    0.63
    特征
    0.63
     features
    0.62
    FEATURE
    0.60
    Features
    0.59
    Act Density 0.018%

    No Known Activations