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

    Neuronpedia

    INDEX
    Explanations

    long-range dependencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    更换
    0.43
     Vegas
    0.40
    Má
    0.39
     Ginger
    0.39
     unity
    0.39
    胭脂
    0.39
     집에
    0.38
    Après
    0.38
    Ginger
    0.38
     whats
    0.37
    POSITIVE LOGITS
     Reh
    0.45
    shah
    0.42
    ೇಖ
    0.41
    អាច
    0.40
    presidente
    0.40
    дор
    0.39
    επ
    0.38
    евич
    0.38
     മനസ്സ
    0.38
     मंत्रिमंडल
    0.38
    Act Density 0.004%

    No Known Activations