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

    Neuronpedia

    INDEX
    Explanations

    oral

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fitness
    -0.08
    fitness
    -0.08
    Neces
    -0.08
     gradients
    -0.08
    �
    -0.08
    출장
    -0.08
    λώ
    -0.08
    gradient
    -0.08
    화
    -0.08
    Gradient
    -0.08
    POSITIVE LOGITS
     resources
    0.08
     справ
    0.08
    资源
    0.08
     under
    0.08
     (
    0.07
     modernes
    0.07
     ресурс
    0.07
     recursos
    0.07
     prever
    0.07
     anton
    0.07
    Act Density 0.002%

    No Known Activations