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

    Neuronpedia

    INDEX
    Explanations

    Metadata, Image, HTTPS, Ring, Condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अनुराग
    0.46
     телеви
    0.46
     родился
    0.43
     계산
    0.40
     ລັບ
    0.40
     гео
    0.40
    📤
    0.40
    ͐
    0.39
     защита
    0.39
    ্রের
    0.39
    POSITIVE LOGITS
     Am
    0.37
    ↵↵
    0.35
     الأم
    0.34
    dbo
    0.34
    müş
    0.34
     taff
    0.33
     Cie
    0.33
     murky
    0.33
    0.33
     ABO
    0.32
    Act Density 0.010%

    No Known Activations