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

    Neuronpedia

    INDEX
    Explanations

    专家

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cay
    -0.08
     rentrer
    -0.08
     сахар
    -0.08
     matern
    -0.08
     eventueel
    -0.08
     rentrée
    -0.08
     altera
    -0.08
    'entrée
    -0.07
     caramel
    -0.07
     сда
    -0.07
    POSITIVE LOGITS
     specializing
    0.10
     knowledgeable
    0.09
     experto
    0.09
    Advisor
    0.09
     advisor
    0.08
     Advisor
    0.08
     asesor
    0.08
     Assistant
    0.08
     especializado
    0.08
     tasked
    0.08
    Act Density 0.003%

    No Known Activations