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

    Neuronpedia

    INDEX
    Explanations

    handling of concepts and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intricacies
    0.46
    having
    0.45
     complexities
    0.43
    anu
    0.40
     இப்போது
    0.40
    head
    0.40
    computers
    0.40
    complexity
    0.40
     complejidad
    0.39
     successfully
    0.39
    POSITIVE LOGITS
     dealings
    0.96
     transactions
    0.73
     descriptions
    0.70
     deliveries
    0.70
     interactions
    0.69
     التعامل
    0.68
     handling
    0.67
     responses
    0.67
     portrayal
    0.66
    对待
    0.66
    Act Density 0.015%

    No Known Activations