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

    Neuronpedia

    INDEX
    Explanations

    forms or defines systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лия
    0.38
     кількість
    0.35
     отца
    0.33
    itabbo
    0.32
    financing
    0.32
     vutt
    0.31
     написа
    0.31
     osoba
    0.31
    іл
    0.31
    鿢
    0.31
    POSITIVE LOGITS
     ecosystems
    0.38
     systems
    0.38
     scenes
    0.36
     Systeme
    0.34
     landscapes
    0.33
      
    0.33
    <
    0.33
     webs
    0.32
     complexes
    0.32
     pipelines
    0.32
    Act Density 0.001%

    No Known Activations