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

    Neuronpedia

    INDEX
    Explanations

    terms related to feature selection and descriptor extraction in machine learning contexts

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

    extracting feature locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.49
     night
    -0.45
    Біографія
    -0.44
    ="@+
    -0.43
     GenerationType
    -0.43
     snippetHide
    -0.41
    night
    -0.40
     autorytatywna
    -0.40
    phazard
    -0.39
    这张
    -0.39
    POSITIVE LOGITS
    NameInMap
    0.50
    이터
    0.42
     extraction
    0.41
    extraction
    0.41
    nsics
    0.40
    素材
    0.39
     extractor
    0.39
    eradish
    0.39
    VertexAttrib
    0.39
    Chandigarh
    0.39
    Act Density 0.049%

    No Known Activations