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

    Neuronpedia

    INDEX
    Explanations

    code/mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (categories
    -0.06
     Verizon
    -0.06
     ايران
    -0.06
     bytes
    -0.06
    _And
    -0.06
    _press
    -0.06
    Gatt
    -0.06
    anson
    -0.06
    alu
    -0.06
     D
    -0.06
    POSITIVE LOGITS
    .progress
    0.06
    catid
    0.06
    шается
    0.06
     PID
    0.06
     liabilities
    0.06
     mục
    0.06
    	ORDER
    0.06
     seksi
    0.06
     fark
    0.06
    _meta
    0.06
    Act Density 0.063%

    No Known Activations