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

    Neuronpedia

    INDEX
    Explanations

    references to matrices in mathematical contexts

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

    matrix and matrices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UseVisualStyle
    -0.39
     &___
    -0.36
     createSlice
    -0.35
    destroyAll
    -0.34
     leſs
    -0.33
     deſt
    -0.32
     ſmall
    -0.32
    と思っています
    -0.32
     juſt
    -0.31
    <tbody>
    -0.31
    POSITIVE LOGITS
    matrix
    2.94
     matrix
    2.06
    Matrix
    1.89
     Matrix
    1.80
     MATRIX
    1.70
    MATRIX
    1.65
    matrices
    1.41
     matrices
    1.37
    矩阵
    1.34
     Matrices
    1.20
    Act Density 0.012%

    No Known Activations