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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to matrix decomposition and singular value analysis

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

    Mathematical equations and matrix notation

    np_acts-logits-general · gemini-2.0-flash

    matrix and math notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.89
     Dra
    -0.50
    amaño
    -0.50
    profession
    -0.49
    duty
    -0.48
     abbandon
    -0.47
    bjs
    -0.47
    versiti
    -0.47
     duty
    -0.46
     abrasion
    -0.46
    POSITIVE LOGITS
     matrix
    0.92
     Matrix
    0.83
     matrices
    0.77
     matriz
    0.75
     matrice
    0.74
    Matrix
    0.73
    matrix
    0.71
    矩阵
    0.69
     AspNetCore
    0.67
     Matrices
    0.67
    Act Density 1.274%

    No Known Activations