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

    Neuronpedia

    INDEX
    Explanations

    precision

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	file
    -0.07
     Ly
    -0.07
     Lar
    -0.06
     Flynn
    -0.06
     Ange
    -0.06
     Robots
    -0.06
     WTO
    -0.06
    .Cache
    -0.06
     olm
    -0.06
    fly
    -0.06
    POSITIVE LOGITS
     precision
    0.09
     Precision
    0.08
    Production
    0.07
     speed
    0.07
    precision
    0.07
     friction
    0.07
     production
    0.07
    _precision
    0.06
    in
    0.06
     specifications
    0.06
    Act Density 0.003%

    No Known Activations