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

    Neuronpedia

    INDEX
    Explanations

    matrix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vl
    -0.07
    fuck
    -0.07
    adol
    -0.07
     greeting
    -0.07
    -su
    -0.06
    ывая
    -0.06
     Invalidate
    -0.06
    也不
    -0.06
     prol
    -0.06
    غيل
    -0.06
    POSITIVE LOGITS
     matrix
    0.11
     Matrix
    0.10
     mtx
    0.08
    matrix
    0.08
    μά
    0.08
    _mtx
    0.07
     Maz
    0.07
    (matrix
    0.07
    (Matrix
    0.07
    atz
    0.07
    Act Density 0.012%

    No Known Activations