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

    Neuronpedia

    INDEX
    Explanations

    AI assistant uncertainty/clarification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ursor
    -0.09
    Rum
    -0.08
    Ị
    -0.08
     likes
    -0.07
    Cells
    -0.07
     basal
    -0.07
     presses
    -0.07
     coolant
    -0.07
    ịch
    -0.07
    ással
    -0.07
    POSITIVE LOGITS
    _invalid
    0.09
     طرف
    0.09
     aquello
    0.08
     юу
    0.08
     parto
    0.08
     logically
    0.08
     Vorge
    0.08
     неожидан
    0.08
     thata
    0.08
     heta
    0.08
    Act Density 0.012%

    No Known Activations