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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	data
    -0.07
    (static
    -0.07
    deb
    -0.06
    ного
    -0.06
    seen
    -0.06
     cycling
    -0.06
     clinical
    -0.06
     ||↵
    -0.06
    stride
    -0.06
     athletes
    -0.06
    POSITIVE LOGITS
     nek
    0.08
    AUSE
    0.06
    MW
    0.06
    ].[
    0.06
     ET
    0.06
    [:
    0.06
    inks
    0.06
    Jets
    0.06
    essenger
    0.06
    (Id
    0.06
    Act Density 0.002%

    No Known Activations