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

    Neuronpedia

    INDEX
    Explanations

    break

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cuales
    -0.07
     Джон
    -0.06
    代
    -0.06
     промислов
    -0.06
     плен
    -0.06
     mach
    -0.06
    _catalog
    -0.06
    _goto
    -0.06
     ward
    -0.06
     disposed
    -0.06
    POSITIVE LOGITS
    restrict
    0.07
    Summer
    0.07
     лечения
    0.07
    strategy
    0.06
     Documentation
    0.06
    없는
    0.06
    .Edit
    0.06
     ___
    0.06
    	S
    0.06
    American
    0.06
    Act Density 0.005%

    No Known Activations