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

    Neuronpedia

    INDEX
    Explanations

    mathematical terminology related to matrices and eigenvalues

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

    "Matrix" or words near "matrix"

    np_acts-logits-general · gemini-2.0-flash

    matrix properties and tests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    campe
    -0.53
     kling
    -0.51
    xtext
    -0.50
     Galvan
    -0.49
    eara
    -0.49
    ยะ
    -0.47
    HORE
    -0.46
     perlas
    -0.46
    Chandigarh
    -0.46
     Tit
    -0.46
    POSITIVE LOGITS
     matrix
    1.57
     Matrix
    1.40
     matrices
    1.37
    matrix
    1.31
    Matrix
    1.29
     MATRIX
    1.24
     matrice
    1.17
     Matrices
    1.16
    矩阵
    1.15
     matriz
    1.13
    Act Density 1.312%

    No Known Activations