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

    Neuronpedia

    INDEX
    Explanations

    matrix determinants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shout
    -0.08
    annelse
    -0.08
    Annonce
    -0.08
     neues
    -0.08
    annar
    -0.07
    説
    -0.07
    аться
    -0.07
     perdre
    -0.07
     pię
    -0.07
     scream
    -0.07
    POSITIVE LOGITS
     matrices
    0.11
    Matrices
    0.09
    Diagonal
    0.08
     diagonal
    0.08
     agility
    0.08
    matrix
    0.08
     matrix
    0.07
     aqu
    0.07
    فاءة
    0.07
    	Matrix
    0.07
    Act Density 0.020%

    No Known Activations