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

    Neuronpedia

    INDEX
    Explanations

    varied/introductory text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    Long
    -0.06
     glacier
    -0.06
     محیط
    -0.06
     dust
    -0.06
     sab
    -0.06
     lofty
    -0.06
     tall
    -0.06
     liters
    -0.06
    鼓
    -0.06
    POSITIVE LOGITS
     besten
    0.07
    销
    0.07
     pang
    0.06
     mage
    0.06
    queryString
    0.06
     vorhand
    0.06
     raspberry
    0.06
     sind
    0.06
    GameState
    0.06
    .ui
    0.06
    Act Density 0.286%

    No Known Activations