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

    Neuronpedia

    INDEX
    Explanations

    tools and resources for development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    that
    0.16
     one
    0.16
     ۔
    0.15
     அந்தக்
    0.15
    這個
    0.15
     dictum
    0.15
    this
    0.15
    一個
    0.15
     वाला
    0.14
    一
    0.14
    POSITIVE LOGITS
     herramientas
    0.21
     budgets
    0.21
     scholarships
    0.20
     infrastructure
    0.20
     tools
    0.20
     sponsorships
    0.19
     incentives
    0.19
     collaborations
    0.19
     regulations
    0.19
     partnerships
    0.19
    Act Density 3.382%

    No Known Activations