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

    Neuronpedia

    INDEX
    Explanations

    matrix and matrices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sábado
    0.60
     tytu
    0.57
     água
    0.56
     disenfranch
    0.56
     taver
    0.55
     étro
    0.55
     Sabtu
    0.54
    气息
    0.54
     advogado
    0.53
     turístico
    0.53
    POSITIVE LOGITS
     matrix
    1.33
     matrices
    1.28
    matrix
    1.16
    Matrix
    1.13
    Matrices
    1.09
     Matrices
    1.05
    矩阵
    1.01
     Matrix
    0.99
    matrices
    0.99
     transpose
    0.92
    Act Density 0.279%

    No Known Activations