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

    Neuronpedia

    INDEX
    Explanations

    Legislative bodies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BR
    -0.07
     marital
    -0.07
     Dam
    -0.07
    (values
    -0.07
    üyordu
    -0.06
    Baby
    -0.06
    &E
    -0.06
    běhu
    -0.06
    ?>↵↵↵
    -0.06
    arf
    -0.06
    POSITIVE LOGITS
     Covent
    0.07
     Св
    0.06
     düş
    0.06
    /mail
    0.06
    tings
    0.06
    .public
    0.06
    	constexpr
    0.06
    zbollah
    0.06
    Optimizer
    0.06
     Autism
    0.06
    Act Density 0.013%

    No Known Activations