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

    Neuronpedia

    INDEX
    Explanations

    latex formatting and math symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    χ
    0.79
    ทาง
    0.75
    ってる
    0.75
    タン
    0.74
     ELECTRON
    0.70
     encapsulated
    0.68
     visible
    0.68
    っている
    0.68
    ⁎
    0.68
     variation
    0.67
    POSITIVE LOGITS
     తప్ప
    0.97
    {
    0.95
    til
    0.90
     vadati
    0.90
     හැකි
    0.89
    tedir
    0.87
    Fatalf
    0.87
    נטי
    0.87
    క్కడ
    0.86
    {$
    0.85
    Act Density 0.037%

    No Known Activations