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

    Neuronpedia

    INDEX
    Explanations

    resources and capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     con
    0.50
     huh
    0.46
     o
    0.44
     semua
    0.44
     của
    0.44
     al
    0.43
     tally
    0.43
     it
    0.43
    Lu
    0.43
     Luigi
    0.43
    POSITIVE LOGITS
     расте
    0.49
    लांग
    0.49
     ресур
    0.48
    ුණ
    0.46
    resources
    0.46
     Ressourcen
    0.45
    硬盘
    0.44
    迳
    0.43
    лини
    0.43
    Resources
    0.42
    Act Density 0.015%

    No Known Activations