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

    Neuronpedia

    INDEX
    Explanations

    expertise and capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     озна
    0.43
     Educ
    0.41
     Growth
    0.40
     शिक्षित
    0.39
     discour
    0.38
     nowrap
    0.38
    Educ
    0.37
    虬
    0.37
    Growth
    0.37
    沟通
    0.36
    POSITIVE LOGITS
     expertise
    1.71
    expertise
    1.55
     Expertise
    1.45
     capabilities
    1.03
     эксперти
    1.03
    capabilities
    0.98
     Capabilities
    0.88
    Capabilities
    0.87
     capacidades
    0.81
     capability
    0.79
    Act Density 0.019%

    No Known Activations