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

    Neuronpedia

    INDEX
    Explanations

    watch/monitor followed by relation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     infrastructures
    0.50
     institutions
    0.50
     sites
    0.49
     infrastructure
    0.47
     infrastrukt
    0.47
     melts
    0.45
     startups
    0.45
     pain
    0.45
     organizations
    0.45
     finiteness
    0.45
    POSITIVE LOGITS
    inescent
    0.47
     تقویت
    0.47
    یل
    0.46
    empatan
    0.46
     उपयोग
    0.45
     plenum
    0.45
    ☭
    0.45
    zej
    0.45
     drugih
    0.45
     توڑ
    0.45
    Act Density 0.001%

    No Known Activations