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

    Neuronpedia

    INDEX
    Explanations

    pool

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     difficult
    -0.08
    .viewer
    -0.08
    ển
    -0.08
     før
    -0.08
     revised
    -0.07
     ví
    -0.07
     הפ
    -0.07
     soc
    -0.07
     larga
    -0.07
     difícil
    -0.07
    POSITIVE LOGITS
    Sensors
    0.09
    Executor
    0.08
     Regina
    0.08
     выполнения
    0.08
     Tasks
    0.08
    executor
    0.08
     карточ
    0.07
    Он
    0.07
    Completion
    0.07
     Executors
    0.07
    Act Density 0.000%

    No Known Activations